Paper Citation Record · LEDGER

Towards Action Hijacking of Large Language Model-based Agent

As of 17 August 2026, this Paper Citation Record lists 100 of 143 outbound references and 9 inbound Pith citation observations for arXiv:2412.10807.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2412.10807 v2

Coverage vector

measured 100 of 143 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T15:41:57.677272Z

measured 109 of 109 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:16:52.634434Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

100 of 143 outbound references displayed

verified exact1
verified fuzzy0
unresolved99
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

3
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 9a8d25c5-80a3-4461-81df-21004d491235 · outbound

This paper cites A survey on rag meeting llms: Towards retrieval-augmented large language models,.

Towards Action Hijacking of Large Language Model-based Agent A survey on rag meeting llms: Towards retrieval-augmented large language models,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:56.980826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94c15c2d-a850-4708-be30-91e3a6a18b83 · outbound

This paper cites Will affective computing emerge from foundation models and general artificial intelligence? a first evaluation of chatgpt,.

Towards Action Hijacking of Large Language Model-based Agent Will affective computing emerge from foundation models and general artificial intelligence? a first evaluation of chatgpt,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:56.998650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fa84e38-87a4-4482-913f-65d67bf890df · outbound

This paper cites Pleak: Prompt leaking attacks against large language model applications,.

Towards Action Hijacking of Large Language Model-based Agent Pleak: Prompt leaking attacks against large language model applications,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.010667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fb53507-5d7d-49b0-aaa0-6a81dee45bf2 · outbound

This paper cites Tptu: Task planning and tool usage of large language model-based ai agents,.

Towards Action Hijacking of Large Language Model-based Agent Tptu: Task planning and tool usage of large language model-based ai agents,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.015937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e52f8702-1d55-44f9-a23e-c9401cf4f303 · outbound

This paper cites Large language models in finance: A survey,.

Towards Action Hijacking of Large Language Model-based Agent Large language models in finance: A survey,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.030587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a81d61b-31f5-415d-ad2c-f1c658c50bf7 · outbound

This paper cites Bots with feelings: Should ai agents express positive emotion in customer service?.

Towards Action Hijacking of Large Language Model-based Agent Bots with feelings: Should ai agents express positive emotion in customer service?

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.037527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 488cb7e3-bbb5-4735-88b0-ee796dbad2c5 · outbound

This paper cites Osagent: Copiloting operating system with llm-based agent,.

Towards Action Hijacking of Large Language Model-based Agent Osagent: Copiloting operating system with llm-based agent,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.055452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 736b71aa-7093-4d4e-89be-5e14c1dcd9de · outbound

This paper cites Ai agents under threat: A survey of key security challenges and future pathways,.

Towards Action Hijacking of Large Language Model-based Agent Ai agents under threat: A survey of key security challenges and future pathways,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.072647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27a42118-9105-4e45-b981-4488d8e8273b · outbound

This paper cites Generative agents: Interactive simulacra of human behavior,.

Towards Action Hijacking of Large Language Model-based Agent Generative agents: Interactive simulacra of human behavior,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.086101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dedef4a-2192-473e-95ef-b0df41696fc2 · outbound

This paper cites Multisql: A schema-integrated context-dependent text2sql dataset with diverse sql operations,.

Towards Action Hijacking of Large Language Model-based Agent Multisql: A schema-integrated context-dependent text2sql dataset with diverse sql operations,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.092950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e08d164-bec3-4a7b-a07d-938b2688fdf4 · outbound

This paper cites From multimodal llm to human-level ai: Modality, instruction, reasoning, efficiency and beyond,.

Towards Action Hijacking of Large Language Model-based Agent From multimodal llm to human-level ai: Modality, instruction, reasoning, efficiency and beyond,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.098533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2afeb15c-a38b-40fd-8649-d563e9b205d6 · outbound

This paper cites Minding language models’ (lack of) theory of mind: A plug- and-play multi-character belief tracker,.

Towards Action Hijacking of Large Language Model-based Agent Minding language models’ (lack of) theory of mind: A plug- and-play multi-character belief tracker,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.103853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7803117-fb78-450d-9e10-a883c8e60598 · outbound

This paper cites Gpt-4 vs. gpt-3.5: A concise showdown,.

Towards Action Hijacking of Large Language Model-based Agent Gpt-4 vs. gpt-3.5: A concise showdown,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.109203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7fea724-f31a-4532-8787-dca9d708b7ea · outbound

This paper cites Training language models to follow instructions with human feedback,.

Towards Action Hijacking of Large Language Model-based Agent Training language models to follow instructions with human feedback,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.122164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19922004-b735-4d7e-aef6-53da35db0ab7 · outbound

This paper cites GPT-4 Technical Report.

Towards Action Hijacking of Large Language Model-based Agent GPT-4 Technical Report

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.128157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66500914-c16b-4b9b-8b97-833a3aeeb66d · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Towards Action Hijacking of Large Language Model-based Agent Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.133662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d5b14b8-1a29-4b80-b410-ee16978e6648 · outbound

This paper cites The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only.

Towards Action Hijacking of Large Language Model-based Agent The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.139508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2259319d-b094-4770-9189-181d1dd90f5b · outbound

This paper cites Qwen Technical Report.

Towards Action Hijacking of Large Language Model-based Agent Qwen Technical Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.146558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c34a7646-c71b-46fb-8aa9-8c3a9ccaa5d5 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Towards Action Hijacking of Large Language Model-based Agent Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.152874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8d742f6-a962-4bb6-8908-5537994edc82 · outbound

This paper cites A Survey on Employing Large Language Models for Text-to-SQL Tasks.

Towards Action Hijacking of Large Language Model-based Agent A Survey on Employing Large Language Models for Text-to-SQL Tasks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.160464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92348bd6-104f-4023-86c0-d092e7204f07 · outbound

This paper cites Semantically equivalent adversarial rules for debugging nlp models,.

Towards Action Hijacking of Large Language Model-based Agent Semantically equivalent adversarial rules for debugging nlp models,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.166448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d7b5f62-b383-4e8f-a85b-139059a28487 · outbound

This paper cites Is bert really robust? a strong baseline for natural language attack on text classification and entailment,.

Towards Action Hijacking of Large Language Model-based Agent Is bert really robust? a strong baseline for natural language attack on text classification and entailment,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.172333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4b6511e-8a18-4640-9bcc-7e362750855a · outbound

This paper cites Measure and Improve Robustness in NLP Models: A Survey.

Towards Action Hijacking of Large Language Model-based Agent Measure and Improve Robustness in NLP Models: A Survey

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.177499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 826b4267-439c-4205-b6fd-9703234a4bcf · outbound

This paper cites Expanding Scope: Adapting English Adversarial Attacks to Chinese.

Towards Action Hijacking of Large Language Model-based Agent Expanding Scope: Adapting English Adversarial Attacks to Chinese

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.185173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18704b65-a98c-4726-b2fc-1eabfaf3d25a · outbound

This paper cites Security and privacy challenges of large language models: A survey,.

Towards Action Hijacking of Large Language Model-based Agent Security and privacy challenges of large language models: A survey,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.192813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9268fdea-abac-4f3d-996e-8321f17fc3a4 · outbound

This paper cites Don’t listen to me: understanding and exploring jailbreak prompts of large language models,.

Towards Action Hijacking of Large Language Model-based Agent Don’t listen to me: understanding and exploring jailbreak prompts of large language models,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.198901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a8139b5-793f-4bb5-94ee-6e4b0e56f9aa · outbound

This paper cites Mma- diffusion: Multimodal attack on diffusion models,.

Towards Action Hijacking of Large Language Model-based Agent Mma- diffusion: Multimodal attack on diffusion models,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.203737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53f12e35-e038-4d65-86a2-f5cea26f98da · outbound

This paper cites LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples.

Towards Action Hijacking of Large Language Model-based Agent LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.209379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de426f70-0acf-44d6-9ce8-a015a4b3d8e3 · outbound

This paper cites From prompt injections to sql injection attacks: How protected is your llm- integrated web application?.

Towards Action Hijacking of Large Language Model-based Agent From prompt injections to sql injection attacks: How protected is your llm- integrated web application?

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.215614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b8717e1-6098-4531-ad4f-8b7301e4d884 · outbound

This paper cites Synthetic-Text-To-SQL: A synthetic dataset for training language models to generate sql queries from natural language prompts,.

Towards Action Hijacking of Large Language Model-based Agent Synthetic-Text-To-SQL: A synthetic dataset for training language models to generate sql queries from natural language prompts,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.227506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 615263cc-e378-4db0-ae22-c30cabf96f67 · outbound

This paper cites Sneakyprompt: Jailbreaking text-to-image generative models,.

Towards Action Hijacking of Large Language Model-based Agent Sneakyprompt: Jailbreaking text-to-image generative models,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.233498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b09f6ef4-ae60-40a9-a86b-7085f79f7a9d · outbound

This paper cites M3e: Moka massive mixed embedding model,.

Towards Action Hijacking of Large Language Model-based Agent M3e: Moka massive mixed embedding model,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.239723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8dde7c5-2308-4161-8512-08f9e8ac70dd · outbound

This paper cites Minilm: Deep self-attention distillation for task-agnostic compression of pre- trained transformers,.

Towards Action Hijacking of Large Language Model-based Agent Minilm: Deep self-attention distillation for task-agnostic compression of pre- trained transformers,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.245849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e191681-0e08-46ca-b9c4-95e05fe5fb24 · outbound

This paper cites Tbta: Token-based textual adversarial attack,.

Towards Action Hijacking of Large Language Model-based Agent Tbta: Token-based textual adversarial attack,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.251668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c908d089-8cd3-4f8c-9bdc-2b3c6cb5cb24 · outbound

This paper cites Bert: Pre- training of deep bidirectional transformers for language understand- ing,.

Towards Action Hijacking of Large Language Model-based Agent Bert: Pre- training of deep bidirectional transformers for language understand- ing,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.258446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77be6fd5-eb6f-4d9e-b671-3b4331eef980 · outbound

This paper cites Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models.

Towards Action Hijacking of Large Language Model-based Agent Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.265233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 269115cb-f94a-4c60-9572-33e8c8652546 · outbound

This paper cites Adversarial text generation by search and learning,.

Towards Action Hijacking of Large Language Model-based Agent Adversarial text generation by search and learning,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.272433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c197a26-cdf5-4856-a823-e6e628a66c95 · outbound

This paper cites Punctuation-level attack: Single-shot and single punctuation attack can fool text models,.

Towards Action Hijacking of Large Language Model-based Agent Punctuation-level attack: Single-shot and single punctuation attack can fool text models,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.280680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84397d80-49d7-472c-9d22-0873de78571a · outbound

This paper cites An LLM can Fool Itself: A Prompt-Based Adversarial Attack.

Towards Action Hijacking of Large Language Model-based Agent An LLM can Fool Itself: A Prompt-Based Adversarial Attack

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.286476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85cddb54-5b88-467a-8350-483f582ab7fb · outbound

This paper cites TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP.

Towards Action Hijacking of Large Language Model-based Agent TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.293134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae213440-1106-4dc3-8369-b1faa54baec3 · outbound

This paper cites OpenAttack: An Open-source Textual Adversarial Attack Toolkit.

Towards Action Hijacking of Large Language Model-based Agent OpenAttack: An Open-source Textual Adversarial Attack Toolkit

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.300332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01375386-517f-4978-8f01-b8f7e6eb5cc7 · outbound

This paper cites Curiosity-driven red-teaming for large language models,.

Towards Action Hijacking of Large Language Model-based Agent Curiosity-driven red-teaming for large language models,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.307977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38358f22-827f-41e3-86c1-0cfaabca05f2 · outbound

This paper cites Jailbroken: How does llm safety training fail?.

Towards Action Hijacking of Large Language Model-based Agent Jailbroken: How does llm safety training fail?

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.314751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81925200-029c-4d36-90f6-4bf7c40668ce · outbound

This paper cites Black-box generation of adversarial text sequences to evade deep learning classifiers,.

Towards Action Hijacking of Large Language Model-based Agent Black-box generation of adversarial text sequences to evade deep learning classifiers,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.323937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e5885c1-83fa-414a-9f10-0776e019797f · outbound

This paper cites Language models as zero-shot planners: Extracting actionable knowledge for embodied agents,.

Towards Action Hijacking of Large Language Model-based Agent Language models as zero-shot planners: Extracting actionable knowledge for embodied agents,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.330045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a7bf646-fc3e-4017-b8b6-afd61731dcaa · outbound

This paper cites Large language models are zero-shot reasoners,.

Towards Action Hijacking of Large Language Model-based Agent Large language models are zero-shot reasoners,

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.337461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2bd0603-0a99-4f1f-8914-540b3dae94a8 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

Towards Action Hijacking of Large Language Model-based Agent Chain-of-thought prompting elicits reasoning in large language models,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.343932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 172bf6b6-76b2-490b-aa51-1150798fcbb6 · outbound

This paper cites React: Synergizing reasoning and acting in language models,.

Towards Action Hijacking of Large Language Model-based Agent React: Synergizing reasoning and acting in language models,

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.349489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc561fb8-3965-4736-8599-b7dbf4685886 · outbound

This paper cites Pal: Program-aided language models,.

Towards Action Hijacking of Large Language Model-based Agent Pal: Program-aided language models,

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.354842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7e33243-f960-435a-b243-d8be2309c768 · outbound

This paper cites Toolformer: Language models can teach themselves to use tools,.

Towards Action Hijacking of Large Language Model-based Agent Toolformer: Language models can teach themselves to use tools,

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.360223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8b334e0-a952-45d7-b48e-f59527258ba4 · outbound

This paper cites Chatgpt and the rise of large language models: the new ai-driven infodemic threat in public health,.

Towards Action Hijacking of Large Language Model-based Agent Chatgpt and the rise of large language models: the new ai-driven infodemic threat in public health,

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.369912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e76d485e-b5ea-4ccb-a48b-d846bb378a71 · outbound

This paper cites Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents.

Towards Action Hijacking of Large Language Model-based Agent Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.376336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80e66199-d13b-4f26-925d-e73f6f8416d8 · outbound

This paper cites A Technological Perspective on Misuse of Available AI.

Towards Action Hijacking of Large Language Model-based Agent A Technological Perspective on Misuse of Available AI

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-08-11T15:41:59.191363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ea7b9116-7fce-4781-b258-d95c4efe39cd · outbound

This paper cites Adversarial Example Generation with Syntactically Controlled Paraphrase Networks.

Towards Action Hijacking of Large Language Model-based Agent Adversarial Example Generation with Syntactically Controlled Paraphrase Networks

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.387617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f16ef15a-8213-4d0f-b3c0-68f5069dcef7 · outbound

This paper cites Generating Natural Adversarial Examples.

Towards Action Hijacking of Large Language Model-based Agent Generating Natural Adversarial Examples

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.392912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acf61475-ce2b-49db-9986-827fe8c142e3 · outbound

This paper cites Generating natural language adversarial examples through probability weighted word saliency,.

Towards Action Hijacking of Large Language Model-based Agent Generating natural language adversarial examples through probability weighted word saliency,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.398816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c49fe721-83c0-434f-a144-215550e073f9 · outbound

This paper cites Word-level Textual Adversarial Attacking as Combinatorial Optimization.

Towards Action Hijacking of Large Language Model-based Agent Word-level Textual Adversarial Attacking as Combinatorial Optimization

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.405600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 364a8a23-be19-440f-9ea0-f5ae32947267 · outbound

This paper cites Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems.

Towards Action Hijacking of Large Language Model-based Agent Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.411512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29d23a11-68cf-4005-b85d-1c7388abf996 · outbound

This paper cites Latent guard: A safety framework for text-to-image generation,.

Towards Action Hijacking of Large Language Model-based Agent Latent guard: A safety framework for text-to-image generation,

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.417430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0853157-c110-4b99-b456-b52c4e8cd4e2 · outbound

This paper cites Effective prompt extraction from language models,.

Towards Action Hijacking of Large Language Model-based Agent Effective prompt extraction from language models,

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.423618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12e963e0-dcef-4713-a4e7-5df9aef8012e · outbound

This paper cites BLOOM: A 176B-Parameter Open-Access Multilingual Language Model.

Towards Action Hijacking of Large Language Model-based Agent BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.428970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12c96737-0907-41b2-a2ec-797cd1ce0041 · outbound

This paper cites Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization.

Towards Action Hijacking of Large Language Model-based Agent Efficient Universal Goal Hijacking with Semantics-guided Prompt Organization

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.435698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 379c5682-e7fd-426f-887c-01397550cddd · outbound

This paper cites Large language models can be easily distracted by irrelevant context,.

Towards Action Hijacking of Large Language Model-based Agent Large language models can be easily distracted by irrelevant context,

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.441475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 813a40c4-2f4c-4aaf-9260-a61897d80082 · outbound

This paper cites Hijacking large language models via adversarial in- context learning,.

Towards Action Hijacking of Large Language Model-based Agent Hijacking large language models via adversarial in- context learning,

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.446281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c3f24df-8b9c-4904-a610-ed43a531489d · outbound

This paper cites Hijacking Context in Large Multi-modal Models.

Towards Action Hijacking of Large Language Model-based Agent Hijacking Context in Large Multi-modal Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.451359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adc14932-6c52-4930-b649-7b69c4861698 · outbound

This paper cites What Was Your Prompt? A Remote Keylogging Attack on AI Assistants.

Towards Action Hijacking of Large Language Model-based Agent What Was Your Prompt? A Remote Keylogging Attack on AI Assistants

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.456969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa853daf-bed7-42b3-94d7-2ad121926692 · outbound

This paper cites Coercing LLMs to do and reveal (almost) anything.

Towards Action Hijacking of Large Language Model-based Agent Coercing LLMs to do and reveal (almost) anything

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.462307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e87aee6c-f698-4048-9936-0522d0517905 · outbound

This paper cites Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models.

Towards Action Hijacking of Large Language Model-based Agent Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.467401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5d2b5dc-ec25-4b8f-9ca1-5f18f1edad59 · outbound

This paper cites Agentpoison: Red- teaming llm agents via poisoning memory or knowledge bases,.

Towards Action Hijacking of Large Language Model-based Agent Agentpoison: Red- teaming llm agents via poisoning memory or knowledge bases,

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.474384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc2504fe-8bfd-45fe-9044-943ac76a8a2a · outbound

This paper cites InjecAgent: Bench- marking indirect prompt injections in tool-integrated large language model agents,.

Towards Action Hijacking of Large Language Model-based Agent InjecAgent: Bench- marking indirect prompt injections in tool-integrated large language model agents,

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.480128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92cb36d2-533e-4b53-b438-f709b0a9189b · outbound

This paper cites Automatic chain of thought prompting in large language models,.

Towards Action Hijacking of Large Language Model-based Agent Automatic chain of thought prompting in large language models,

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.488002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c37bd803-1faa-4485-99d5-19570148956a · outbound

This paper cites RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent.

Towards Action Hijacking of Large Language Model-based Agent RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.495607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6635a15-e2c6-40e9-9343-b3927ac0bbad · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models,.

Towards Action Hijacking of Large Language Model-based Agent Tree of thoughts: Deliberate problem solving with large language models,

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.502764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 110e770b-c467-4e9d-b80a-0c62dbfc27be · outbound

This paper cites Mind2web: Towards a generalist agent for the web,.

Towards Action Hijacking of Large Language Model-based Agent Mind2web: Towards a generalist agent for the web,

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.508900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a324b15d-5449-427b-94a5-4d0201383790 · outbound

This paper cites Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models.

Towards Action Hijacking of Large Language Model-based Agent Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.514127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b2fdc1a-d2a8-47b0-a913-52ee2824645f · outbound

This paper cites On Prompt-Driven Safeguarding for Large Language Models.

Towards Action Hijacking of Large Language Model-based Agent On Prompt-Driven Safeguarding for Large Language Models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.520205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbe123a3-f2ae-433b-add6-5bad871234ab · outbound

This paper cites A survey on large language model based autonomous agents,.

Towards Action Hijacking of Large Language Model-based Agent A survey on large language model based autonomous agents,

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.535129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80593e04-8cff-418d-aa52-1baa6060ab92 · outbound

This paper cites The Rise and Potential of Large Language Model Based Agents: A Survey.

Towards Action Hijacking of Large Language Model-based Agent The Rise and Potential of Large Language Model Based Agents: A Survey

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.541575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e5be92c-e06f-4279-b96b-05eba8aa855f · outbound

This paper cites The good and the bad: Exploring privacy issues in retrieval-augmented generation (RAG),.

Towards Action Hijacking of Large Language Model-based Agent The good and the bad: Exploring privacy issues in retrieval-augmented generation (RAG),

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.549477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e83fd63e-eb9b-465d-90cf-291187d2a85b · outbound

This paper cites The good and the bad: Exploring privacy issues in retrieval- augmented generation (RAG),.

Towards Action Hijacking of Large Language Model-based Agent The good and the bad: Exploring privacy issues in retrieval- augmented generation (RAG),

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.555546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6bc89b3-aef5-4962-8941-7220c6179189 · outbound

This paper cites Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects.

Towards Action Hijacking of Large Language Model-based Agent Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.560929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d6f762f-91d6-444a-affd-49eee4f9e8e8 · outbound

This paper cites A Survey on the Memory Mechanism of Large Language Model based Agents.

Towards Action Hijacking of Large Language Model-based Agent A Survey on the Memory Mechanism of Large Language Model based Agents

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.566568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b65fdd5e-d436-4689-8c62-7959d5f69adc · outbound

This paper cites Fundamental capabilities of large language models and their applications in domain scenarios: A survey,.

Towards Action Hijacking of Large Language Model-based Agent Fundamental capabilities of large language models and their applications in domain scenarios: A survey,

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.572619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04ff59bb-1127-409a-986a-f455a2b33996 · outbound

This paper cites Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies.

Towards Action Hijacking of Large Language Model-based Agent Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.579161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e7b1641-7ec5-4d4e-ac4d-9bedf4100b8a · outbound

This paper cites Prompt Injection attack against LLM-integrated Applications.

Towards Action Hijacking of Large Language Model-based Agent Prompt Injection attack against LLM-integrated Applications

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.586193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94679131-56f7-4ccf-befe-fd5fb1c5393c · outbound

This paper cites Conversational Health Agents: A Personalized LLM-Powered Agent Framework.

Towards Action Hijacking of Large Language Model-based Agent Conversational Health Agents: A Personalized LLM-Powered Agent Framework

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.595623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b9a7f79-02ad-4dfb-9e66-32c2f7eb4259 · outbound

This paper cites MedAgents: Large language models as collaborators for zero-shot medical reasoning,.

Towards Action Hijacking of Large Language Model-based Agent MedAgents: Large language models as collaborators for zero-shot medical reasoning,

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.601828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d8e0778-c8d5-45d2-97f4-26b8181ec0f5 · outbound

This paper cites POSTER: identifying and mitigating vulnerabilities in llm- integrated applications,.

Towards Action Hijacking of Large Language Model-based Agent POSTER: identifying and mitigating vulnerabilities in llm- integrated applications,

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.608337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e020833-a876-403d-8ccf-657ebda3cf44 · outbound

This paper cites Tensor trust: Interpretable prompt injection attacks from an online game,.

Towards Action Hijacking of Large Language Model-based Agent Tensor trust: Interpretable prompt injection attacks from an online game,

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.617277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a68aeca8-b3dc-4b4f-8137-44948b83423c · outbound

This paper cites Not what you’ve signed up for: Compromising real- world llm-integrated applications with indirect prompt injection,.

Towards Action Hijacking of Large Language Model-based Agent Not what you’ve signed up for: Compromising real- world llm-integrated applications with indirect prompt injection,

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.622414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 768852d2-e185-473d-ada8-6e8913260707 · outbound

This paper cites Not what you’ve signed up for: Compromising real- world llm-integrated applications with indirect prompt injection,.

Towards Action Hijacking of Large Language Model-based Agent Not what you’ve signed up for: Compromising real- world llm-integrated applications with indirect prompt injection,

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.627768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09d07956-3344-442e-b2f9-9564eb370fa3 · outbound

This paper cites WIPI: A New Web Threat for LLM-Driven Web Agents.

Towards Action Hijacking of Large Language Model-based Agent WIPI: A New Web Threat for LLM-Driven Web Agents

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.633586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 927597c2-0ab5-4bab-8a59-6c4cd5ba1f9d · outbound

This paper cites Benchmarking and defending against indirect prompt injection attacks on large language models,.

Towards Action Hijacking of Large Language Model-based Agent Benchmarking and defending against indirect prompt injection attacks on large language models,

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.640215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f75fe88-bd5b-4202-82f4-5a5b67f2a35e · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Towards Action Hijacking of Large Language Model-based Agent Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.644948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ea10376-6342-45a8-84ff-6eccaae596c9 · outbound

This paper cites Agent smith: A single image can jailbreak one million mul- timodal LLM agents exponentially fast,.

Towards Action Hijacking of Large Language Model-based Agent Agent smith: A single image can jailbreak one million mul- timodal LLM agents exponentially fast,

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.650357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b493174-7ea7-4568-b522-65d379349f5c · outbound

This paper cites Multi-step jailbreaking privacy attacks on chatgpt,.

Towards Action Hijacking of Large Language Model-based Agent Multi-step jailbreaking privacy attacks on chatgpt,

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.655537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea23651e-4b03-455c-a21c-b73b302643f4 · outbound

This paper cites Poisonedrag: Knowledge poisoning attacks to retrieval-augmented generation of large lan- guage models,.

Towards Action Hijacking of Large Language Model-based Agent Poisonedrag: Knowledge poisoning attacks to retrieval-augmented generation of large lan- guage models,

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.660247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ce47a19-c560-4f28-92c3-e9d47e58c07e · outbound

This paper cites Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications.

Towards Action Hijacking of Large Language Model-based Agent Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications

Reference 102

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.665923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1163cc78-5bbc-4b5f-bc9e-a479cd3653ab · outbound

This paper cites Undefined-oriented programming: De- tecting and chaining prototype pollution gadgets in node. js template engines for malicious consequences,.

Towards Action Hijacking of Large Language Model-based Agent Undefined-oriented programming: De- tecting and chaining prototype pollution gadgets in node. js template engines for malicious consequences,

Reference 103

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.672353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bc5e351-306d-48f6-851d-09f9a9a2adc5 · outbound

This paper cites Certifiably robust rag against retrieval corruption,.

Towards Action Hijacking of Large Language Model-based Agent Certifiably robust rag against retrieval corruption,

Reference 104

Resolution: unresolved; no resolver link, observed 2026-08-11T15:41:57.677272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7e6e8013-39ed-48f8-aa85-1ccbc2d26126 · inbound

Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction cites this paper.

Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction Towards Action Hijacking of Large Language Model-based Agent

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:35.036306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5d8ae3c-194d-47ce-8053-495b49c60c3f · inbound

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents cites this paper.

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents Towards Action Hijacking of Large Language Model-based Agent

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:28:15.536913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae2013fa-4567-474a-894e-f1846bb1a97a · inbound

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem cites this paper.

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Towards Action Hijacking of Large Language Model-based Agent

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-15T19:45:09.827307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7f02b92-2c31-43f7-afec-5de2bedf923e · inbound

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents cites this paper.

A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents Towards Action Hijacking of Large Language Model-based Agent

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T21:34:41.624343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b69c7ee-b7b8-40b0-b7a1-0f4a7edae406 · inbound

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey cites this paper.

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey Towards Action Hijacking of Large Language Model-based Agent

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-05T15:26:33.589505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54f7ea4d-16aa-4788-bd52-0ad2f134c9f2 · inbound

Toward a Safe Internet of Agents cites this paper.

Toward a Safe Internet of Agents Towards Action Hijacking of Large Language Model-based Agent

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-17T03:18:56.838806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d83c0b9e-595c-40b6-b117-9b9f8c9f8092 · inbound

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration cites this paper.

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration Towards Action Hijacking of Large Language Model-based Agent

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-05-09T21:38:30.714205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2b5f4330-b725-46c8-991c-dd3b488cba1b · inbound

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration cites this paper.

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration Towards Action Hijacking of Large Language Model-based Agent

Reference 93

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:32:41.572623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e9121ddc-0084-4c58-b0a5-a12b43efabfc · inbound

Rethinking Agent Security as a Networking Problem cites this paper.

Rethinking Agent Security as a Networking Problem Towards Action Hijacking of Large Language Model-based Agent

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-16T00:16:52.634434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.