Paper Citation Record · LEDGER

LLM Agents Should Employ Security Principles

As of 12 August 2026, this Paper Citation Record lists 90 of 90 outbound references and 18 inbound Pith citation observations for arXiv:2505.24019.

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

pith.paper-citation-record.v1
2505.24019 v1

Coverage vector

measured 90 of 90 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:42:18.393562Z

measured 108 of 108 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 18 of 18 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:33:17.074410Z

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

90 of 90 outbound references displayed

verified exact0
verified fuzzy23
unresolved67
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

2
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation bd985b7c-b0df-459b-8000-298db5310957 · outbound

This paper cites Firewalls to Secure Dynamic LLM Agentic Networks.

LLM Agents Should Employ Security Principles Firewalls to Secure Dynamic LLM Agentic Networks

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:10.530457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5d6c0d8-f456-42ec-a9f2-834243d80537 · outbound

This paper cites Jimenez, Farshad Khorrami, Prashanth Krishnamurthy, Brendan Dolan-Gavitt, Muhammad Shafique, Karthik Narasimhan, Ramesh Karri, and Ofir Press.

LLM Agents Should Employ Security Principles Jimenez, Farshad Khorrami, Prashanth Krishnamurthy, Brendan Dolan-Gavitt, Muhammad Shafique, Karthik Narasimhan, Ramesh Karri, and Ofir Press

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:10.608335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdec2bb5-bbf7-450e-a9ff-048260c07d27 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

LLM Agents Should Employ Security Principles Detecting Language Model Attacks with Perplexity

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:10.698195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d05109fa-289d-4952-ad75-ecd264b038e0 · outbound

This paper cites Generative AI on AWS.https://aws.amazon.com/ai/generative-ai/.

LLM Agents Should Employ Security Principles Generative AI on AWS.https://aws.amazon.com/ai/generative-ai/

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:10.809393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 089e5c0d-478b-43ef-bfa3-b3b54410e83b · outbound

This paper cites AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents.

LLM Agents Should Employ Security Principles AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:10.942106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd089303-22eb-46fd-9132-1b9724232760 · outbound

This paper cites Monitoring computer use via hierarchical summarization.

LLM Agents Should Employ Security Principles Monitoring computer use via hierarchical summarization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.032707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ff1aaba-0123-4546-9680-1d68c64f885f · outbound

This paper cites Introducing the Model Context Protocol, 2024.https://www.anthropic.com/news/model-context-protocol.

LLM Agents Should Employ Security Principles Introducing the Model Context Protocol, 2024.https://www.anthropic.com/news/model-context-protocol

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.133502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be791b63-2bd7-4f41-afd4-8331c45673cb · outbound

This paper cites https://github.com/microsoft/autogen/.

LLM Agents Should Employ Security Principles https://github.com/microsoft/autogen/

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.217203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d65cd2b0-10c3-4be9-bb2e-824e744adbb6 · outbound

This paper cites AirGapAgent: Protecting privacy-conscious conversational agents.

LLM Agents Should Employ Security Principles AirGapAgent: Protecting privacy-conscious conversational agents

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.321358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d64ee457-9957-4055-8516-91b05dfbe8bd · outbound

This paper cites International AI Safety Report.

LLM Agents Should Employ Security Principles International AI Safety Report

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.396694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbcb2b21-ad46-4d62-a163-76dcfe37b233 · outbound

This paper cites Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment.

LLM Agents Should Employ Security Principles Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.476447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd117973-b3e8-4121-a09d-423378211520 · outbound

This paper cites Computer Security: Art and Science.

LLM Agents Should Employ Security Principles Computer Security: Art and Science

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.571062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d9940fd-8a91-4caa-9895-691e6f6f76d3 · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020.

LLM Agents Should Employ Security Principles Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.674312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d347328e-ca07-425f-b855-b3af2492b132 · outbound

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

LLM Agents Should Employ Security Principles Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.749191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 867af2a8-de4d-4a33-8869-65aa2047e972 · outbound

This paper cites Agentpoison: Red-teaming LLM agents via poisoning memory or knowledge bases.Advances in Neural Information Processing Systems, 37:130185–130213, 2024.

LLM Agents Should Employ Security Principles Agentpoison: Red-teaming LLM agents via poisoning memory or knowledge bases.Advances in Neural Information Processing Systems, 37:130185–130213, 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.823955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 596ee284-0ea0-4129-8f46-0a457afe19d0 · outbound

This paper cites LlamaFirewall: An open source guardrail system for building secure AI agents.

LLM Agents Should Employ Security Principles LlamaFirewall: An open source guardrail system for building secure AI agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:11.956892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2892f98d-6ca6-4c1c-a487-fc9581d063d9 · outbound

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

LLM Agents Should Employ Security Principles Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:12.078265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fcb89fa-0184-401d-bb07-7ef9b69a6a92 · outbound

This paper cites LLMs for Customer Service and Support.

LLM Agents Should Employ Security Principles LLMs for Customer Service and Support

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:12.185759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceb442c8-68b9-40a3-8631-22abaefc089f · outbound

This paper cites AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents.

LLM Agents Should Employ Security Principles AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:12.263611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25525d58-b3c5-4ba9-805e-03c7bf4cf5dc · outbound

This paper cites A practical memory injection attack against LLM agents.arXiv preprint arXiv:2503.03704, 2025.

LLM Agents Should Employ Security Principles A practical memory injection attack against LLM agents.arXiv preprint arXiv:2503.03704, 2025

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:12.351103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daed623c-b688-44db-a438-1e84c1d74c33 · outbound

This paper cites LLM Agents can Autonomously Hack Websites.

LLM Agents Should Employ Security Principles LLM Agents can Autonomously Hack Websites

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:12.460789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b98b3fef-4049-4ffc-ac4c-0154f96d31d3 · outbound

This paper cites Papillon: Efficient and stealthy fuzz testing-powered jailbreaks for llms.

LLM Agents Should Employ Security Principles Papillon: Efficient and stealthy fuzz testing-powered jailbreaks for llms

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:25.991712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 59849ad6-626a-4837-baa2-6e83386a7dcd · outbound

This paper cites Announcing the Agent2Agent Protocol (A2A), 2025.

LLM Agents Should Employ Security Principles Announcing the Agent2Agent Protocol (A2A), 2025

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:25.889907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation eef13c70-b45a-442e-ae02-560f42321cae · outbound

This paper cites Redcode: Risky code execution and generation benchmark for code agents.Advances in Neural Information Processing Systems, 37:106190–106236, 2024.

LLM Agents Should Employ Security Principles Redcode: Risky code execution and generation benchmark for code agents.Advances in Neural Information Processing Systems, 37:106190–106236, 2024

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:25.790524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 96993d6c-dce1-4cbf-b163-c9a0afd3c2b9 · outbound

This paper cites Defending Against Indirect Prompt Injection Attacks With Spotlighting.

LLM Agents Should Employ Security Principles Defending Against Indirect Prompt Injection Attacks With Spotlighting

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:12.836704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83cb01ea-f7e7-4ada-a985-5faed646f991 · outbound

This paper cites TrustAgent: Towards Safe and Trustworthy LLM-based Agents.

LLM Agents Should Employ Security Principles TrustAgent: Towards Safe and Trustworthy LLM-based Agents

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:12.942186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c1f3d12-d2ea-4e88-a032-f246d074d031 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

LLM Agents Should Employ Security Principles Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:13.041837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e070e8a2-7038-46cc-8d1e-ec256ef640c2 · outbound

This paper cites DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines.

LLM Agents Should Employ Security Principles DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:13.159532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30dc0c33-a749-4094-8680-eaa2a1479476 · outbound

This paper cites https://github.com/langchain-ai/langchain.

LLM Agents Should Employ Security Principles https://github.com/langchain-ai/langchain

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:25.630328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 03efd940-4c6a-4584-833c-436b070c380c · outbound

This paper cites Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems.

LLM Agents Should Employ Security Principles Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:13.333338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9961eabc-da01-4075-8d8c-7ca6e07d3d7a · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

LLM Agents Should Employ Security Principles DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:13.406934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9efe313b-f1dc-4273-a168-662a114e3017 · outbound

This paper cites RAIN: Your language models can align themselves without finetuning.

LLM Agents Should Employ Security Principles RAIN: Your language models can align themselves without finetuning

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:25.448589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ef746f30-99ce-46c0-b78d-883f9882a0a9 · outbound

This paper cites Agentorca: A dual-system framework to evaluate language agents on operational routine and constraint adherence, 2025.

LLM Agents Should Employ Security Principles Agentorca: A dual-system framework to evaluate language agents on operational routine and constraint adherence, 2025

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:25.310516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c56f5cee-ca82-4ebd-9976-a68fe5bcdde3 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

LLM Agents Should Employ Security Principles AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:13.581416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ba3acef-79e5-48ee-86b5-c7196eac569b · outbound

This paper cites Automatic and Universal Prompt Injection Attacks against Large Language Models.

LLM Agents Should Employ Security Principles Automatic and Universal Prompt Injection Attacks against Large Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:13.656779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94717349-e1fe-4ad4-a098-bb4a1eefcca5 · outbound

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

LLM Agents Should Employ Security Principles Prompt Injection attack against LLM-integrated Applications

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:13.736788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4076bcf0-2259-46ef-b7b3-4336c42dee73 · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses.

LLM Agents Should Employ Security Principles Formalizing and benchmarking prompt injection attacks and defenses

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:13.810103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63ce2e3b-8681-4ef4-932a-ae59ee8ac81d · outbound

This paper cites Tree of attacks: Jailbreaking black-box llms automatically.NeurIPS, 2024.

LLM Agents Should Employ Security Principles Tree of attacks: Jailbreaking black-box llms automatically.NeurIPS, 2024

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:25.058794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 58de7286-4c36-43da-907b-85ec38fcfd78 · outbound

This paper cites Secure data with zero trust.https://learn.microsoft.com/en-us/security/zero-trust/deploy/data.

LLM Agents Should Employ Security Principles Secure data with zero trust.https://learn.microsoft.com/en-us/security/zero-trust/deploy/data

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:24.926146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 01f8cddd-f5a4-45f6-9135-eaae55082fa6 · outbound

This paper cites GPT-4 technical report, 2023.

LLM Agents Should Employ Security Principles GPT-4 technical report, 2023

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:14.016657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3203619-4d85-4a8c-ab2a-f8420dd879cf · outbound

This paper cites Optimizing instructions and demonstrations for multi-stage language model programs.

LLM Agents Should Employ Security Principles Optimizing instructions and demonstrations for multi-stage language model programs

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:24.731074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b6d67e25-53c6-461b-aa1d-e997e1b703d6 · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

LLM Agents Should Employ Security Principles Ignore Previous Prompt: Attack Techniques For Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:14.183326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8526a788-4653-4897-8018-f8bda732c331 · outbound

This paper cites The sandwich defense, 2024.

LLM Agents Should Employ Security Principles The sandwich defense, 2024

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:24.609888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6a19f497-1e9f-4732-8da4-fc51e0ab031d · outbound

This paper cites Fine-tuned deberta-v3-base for prompt injection detection, 2024.

LLM Agents Should Employ Security Principles Fine-tuned deberta-v3-base for prompt injection detection, 2024

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:24.391206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 39a7815c-9f5a-4977-b7ee-6fcf06d14461 · outbound

This paper cites Llm-based agentic systems in medicine and healthcare.Nature Machine Intelligence, 6(12):1418–1420, 2024.

LLM Agents Should Employ Security Principles Llm-based agentic systems in medicine and healthcare.Nature Machine Intelligence, 6(12):1418–1420, 2024

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:14.349072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf62a05f-e636-4597-af89-a63000ad4fd1 · outbound

This paper cites Improving language understanding by generative pre-training.

LLM Agents Should Employ Security Principles Improving language understanding by generative pre-training

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:14.458743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b095827c-cbd0-499c-9369-795dbcd17625 · outbound

This paper cites Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019.

LLM Agents Should Employ Security Principles Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:24.067470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e92c744a-dbb5-4a26-ab6a-45083317a23a · outbound

This paper cites Identifying the risks of lm agents with an lm-emulated sandbox.

LLM Agents Should Employ Security Principles Identifying the risks of lm agents with an lm-emulated sandbox

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:14.597041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ea5a6d0-fd10-4acd-97a8-9e32e13e4d39 · outbound

This paper cites Saltzer and Michael D.

LLM Agents Should Employ Security Principles Saltzer and Michael D

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:23.926538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 12f99703-4403-4662-8a8c-f52513336761 · outbound

This paper cites Scalable and transferable black-box jailbreaks for language models via persona modulation.

LLM Agents Should Employ Security Principles Scalable and transferable black-box jailbreaks for language models via persona modulation

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:23.847173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2c2bde08-6264-4a0e-8f08-47e16c10a20c · outbound

This paper cites PrivacyLens: Evaluating privacy norm awareness of language models in action.

LLM Agents Should Employ Security Principles PrivacyLens: Evaluating privacy norm awareness of language models in action

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:23.711449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ed2e0c91-b822-4f97-aeaf-90334fe082a8 · outbound

This paper cites Collaborative gym: A framework for enabling and evaluating human-agent collaboration.arXiv preprint arXiv:2412.15701, 2024.

LLM Agents Should Employ Security Principles Collaborative gym: A framework for enabling and evaluating human-agent collaboration.arXiv preprint arXiv:2412.15701, 2024

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:14.965587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 490b3d32-0aaf-4692-91a5-47f4cf418e97 · outbound

This paper cites "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models.

LLM Agents Should Employ Security Principles "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:15.041346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7913acda-421d-4cda-b47a-e7e91e03b39d · outbound

This paper cites Choquette-Choo, Milad Nasr, Chawin Sitawarin, Gena Gibson, Andreas Terzis, and John "Four" Flynn.

LLM Agents Should Employ Security Principles Choquette-Choo, Milad Nasr, Chawin Sitawarin, Gena Gibson, Andreas Terzis, and John "Four" Flynn

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:23.568018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 62a2d446-309d-4e3a-bdec-858410c0b0e0 · outbound

This paper cites Progent: Securing AI Agents with Privilege Control.

LLM Agents Should Employ Security Principles Progent: Securing AI Agents with Privilege Control

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:15.258181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66496283-4700-425d-8a6a-d96b84f88a3d · outbound

This paper cites Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles.

LLM Agents Should Employ Security Principles Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:15.340645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e370c83-7e1d-49cb-bf5a-fd9b142233aa · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

LLM Agents Should Employ Security Principles LLaMA: Open and Efficient Foundation Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:15.374992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49bcb3ce-1f1a-4aa2-b8ed-f22c0a351464 · outbound

This paper cites Contextual Agent Security: A Policy for Every Purpose.

LLM Agents Should Employ Security Principles Contextual Agent Security: A Policy for Every Purpose

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:15.456892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccc84b4b-c405-43f6-a854-5b58edeb97bc · outbound

This paper cites Unveiling Privacy Risks in LLM Agent Memory.

LLM Agents Should Employ Security Principles Unveiling Privacy Risks in LLM Agent Memory

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:15.532647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2416549-9e07-4fe0-a7c2-c50da359fe7e · outbound

This paper cites Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models.

LLM Agents Should Employ Security Principles Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:15.631370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e96c548-5365-4c4e-a1c9-ae934e9cf4fd · outbound

This paper cites Jailbroken: How does LLM safety training fail? InNeurIPS, 2023.

LLM Agents Should Employ Security Principles Jailbroken: How does LLM safety training fail? InNeurIPS, 2023

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:23.471413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 002ddea9-086d-45ec-b623-7ae8f92a9849 · outbound

This paper cites IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems.

LLM Agents Should Employ Security Principles IsolateGPT: An Execution Isolation Architecture for LLM-Based Agentic Systems

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:15.770833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 501d3fa2-9165-4f6f-9a3a-612981623685 · outbound

This paper cites Chatarena: Multi-agent language game environments for large language models.https://github.com/chatarena/chatarena, 2023.

LLM Agents Should Employ Security Principles Chatarena: Multi-agent language game environments for large language models.https://github.com/chatarena/chatarena, 2023

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:23.297070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 33867e88-cbca-4552-8a3e-9e4b7474d0df · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments, 2024.

LLM Agents Should Employ Security Principles Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments, 2024

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:15.919093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54353bad-a6dc-49d0-b7fd-50f97b2bc4ab · outbound

This paper cites Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models.

LLM Agents Should Employ Security Principles Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:15.984482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba5b2bdf-6dcb-42ea-9e6d-51a56a1db8fc · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

LLM Agents Should Employ Security Principles GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:16.057577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a35ad4c9-6bde-41a7-aa1a-c4a918fbf45e · outbound

This paper cites LLM-Fuzzer: Scaling assessment of large language model jailbreaks.

LLM Agents Should Employ Security Principles LLM-Fuzzer: Scaling assessment of large language model jailbreaks

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:23.038320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9ecd6738-1a77-4f90-b57a-10e3daf71070 · outbound

This paper cites an unresolved cited work.

LLM Agents Should Employ Security Principles Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:22.780421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8971b96f-62de-484e-9f31-5cfc8ebf7e08 · outbound

This paper cites R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.

LLM Agents Should Employ Security Principles R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:16.267748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b55ef027-4d4d-46ce-81ce-066aa0603d52 · outbound

This paper cites GPT-4 is too smart to be safe: Stealthy chat with LLMs via cipher.

LLM Agents Should Employ Security Principles GPT-4 is too smart to be safe: Stealthy chat with LLMs via cipher

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:22.601536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5dc51e68-0ae0-474a-82ae-456547c0ebde · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.

LLM Agents Should Employ Security Principles InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:16.461006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ac99a43-caa9-4b74-a84e-8675f8bc3679 · outbound

This paper cites Zhang, Joey Ji, Celeste Menders, Riya Dulepet, Thomas Qin, Ron Y.

LLM Agents Should Employ Security Principles Zhang, Joey Ji, Celeste Menders, Riya Dulepet, Thomas Qin, Ron Y

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:22.440904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4adf505c-776b-47ab-bae3-822d609394ca · outbound

This paper cites Goal-guided Generative Prompt Injection Attack on Large Language Models.

LLM Agents Should Employ Security Principles Goal-guided Generative Prompt Injection Attack on Large Language Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:16.635079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b10c2da8-b53b-4941-aedf-cac699e19392 · outbound

This paper cites Agent security bench (ASB): Formalizing and benchmarking attacks and defenses in LLM-based agents.

LLM Agents Should Employ Security Principles Agent security bench (ASB): Formalizing and benchmarking attacks and defenses in LLM-based agents

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:22.322556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6bd88959-2a42-4211-9da3-316e90d52851 · outbound

This paper cites Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction.

LLM Agents Should Employ Security Principles Holistic Automated Red Teaming for Large Language Models through Top-Down Test Case Generation and Multi-turn Interaction

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:16.802912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c4055af-829d-4ce2-946d-b7ff3dcb3103 · outbound

This paper cites Agent-SafetyBench: Evaluating the Safety of LLM Agents.

LLM Agents Should Employ Security Principles Agent-SafetyBench: Evaluating the Safety of LLM Agents

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:16.878014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4aec45b-fb05-4462-b4da-1ef170ba4aa4 · outbound

This paper cites Agentdam: Privacy leakage evaluation for autonomous web agents.arXiv preprint arXiv:2503.09780, 2025.

LLM Agents Should Employ Security Principles Agentdam: Privacy leakage evaluation for autonomous web agents.arXiv preprint arXiv:2503.09780, 2025

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:16.979796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4755f0c4-0df9-493b-bc87-041b609ba668 · outbound

This paper cites RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage.

LLM Agents Should Employ Security Principles RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:17.059726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9c6f5a0-b45e-4e3f-b09c-c24ef5337624 · outbound

This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.

LLM Agents Should Employ Security Principles WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:17.145765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e6c1294-ed3f-4e98-9bd1-d33b70975e5f · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

LLM Agents Should Employ Security Principles Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T12:42:17.234871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af664236-e50d-4876-a479-04426623bb7f · outbound

This paper cites an unresolved cited work.

LLM Agents Should Employ Security Principles Unresolved cited work

Reference 81

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:22.222084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d893c327-457a-43bb-a07b-23da90095d20 · outbound

This paper cites an unresolved cited work.

LLM Agents Should Employ Security Principles Unresolved cited work

Reference 82

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:22.117728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6d981ffe-26a1-4e16-a9c6-f9bd07cd4b93 · outbound

This paper cites an unresolved cited work.

LLM Agents Should Employ Security Principles Unresolved cited work

Reference 83

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:21.981233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 068bf66b-2211-4c74-a8f3-0b52c326865f · outbound

This paper cites an unresolved cited work.

LLM Agents Should Employ Security Principles Unresolved cited work

Reference 84

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:21.877047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d0b69c9e-f71d-4e53-8e62-b9548e2a0acd · outbound

This paper cites Output your analysis in a structured JSON format that clearly states permissions for each tool based on the task context and provides DETAILED reasoning.

LLM Agents Should Employ Security Principles Output your analysis in a structured JSON format that clearly states permissions for each tool based on the task context and provides DETAILED reasoning

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:42:21.708644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3379054e-420d-48f9-b4ee-1498a4230ae7 · outbound

This paper cites an unresolved cited work.

LLM Agents Should Employ Security Principles Unresolved cited work

Reference 86

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:21.492939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fabc4ed9-d310-4eb0-a9bc-e162304cd1c5 · outbound

This paper cites an unresolved cited work.

LLM Agents Should Employ Security Principles Unresolved cited work

Reference 87

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:21.276654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a23379ba-d10b-4a84-8488-6a14c06a5562 · outbound

This paper cites an unresolved cited work.

LLM Agents Should Employ Security Principles Unresolved cited work

Reference 88

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:20.946610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3bd0b09a-4f36-4946-aad4-d0ec73c114de · outbound

This paper cites an unresolved cited work.

LLM Agents Should Employ Security Principles Unresolved cited work

Reference 89

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:20.646846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3586a497-e439-41c5-bcb5-2bfc07e1b6ca · outbound

This paper cites an unresolved cited work.

LLM Agents Should Employ Security Principles Unresolved cited work

Reference 90

Resolution: unresolved; raw_fallback, observed 2026-08-07T12:42:20.381960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Pith citing papers

Observation 16f8fd0f-70db-4624-818d-15468c6f285e · inbound

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks cites this paper.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks LLM Agents Should Employ Security Principles

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:17.074410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac2932f3-7626-4f90-8d04-0933120e2807 · inbound

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance cites this paper.

LLMs are Capable of Misaligned Behavior Under Explicit Prohibition and Surveillance LLM Agents Should Employ Security Principles

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:22:59.187197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c43d2ea-12ac-4812-93c2-e9bc600e31ab · inbound

Security Considerations for Artificial Intelligence Agents cites this paper.

Security Considerations for Artificial Intelligence Agents LLM Agents Should Employ Security Principles

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-15T12:40:00.295146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 10df942f-6b11-48c7-a27b-d46eaacc960b · inbound

Parallax: Why AI Agents That Think Must Never Act cites this paper.

Parallax: Why AI Agents That Think Must Never Act LLM Agents Should Employ Security Principles

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:01:04.817173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a4819020-cad8-41ab-9560-085e22e71429 · inbound

A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents cites this paper.

A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents LLM Agents Should Employ Security Principles

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:01:14.315710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e4e679a8-f1a2-420d-a7ab-a670893e7829 · inbound

When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI cites this paper.

When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI LLM Agents Should Employ Security Principles

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T10:46:31.792945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation cb51a1bf-cc9b-4d9b-b170-fe13e60abd32 · inbound

When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI cites this paper.

When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI LLM Agents Should Employ Security Principles

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:55:44.451126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e4d2c026-00c6-45b8-b140-e16f5678ab00 · inbound

When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks cites this paper.

When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks LLM Agents Should Employ Security Principles

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T08:01:33.084545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 65f35965-3cb2-4e70-9c1f-4339f87c9b74 · inbound

Ghost in the Context: Policy-Carriage Integrity in LLM Agents cites this paper.

Ghost in the Context: Policy-Carriage Integrity in LLM Agents LLM Agents Should Employ Security Principles

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:28:00.169507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f948f307-afc6-420e-b662-4c12c1ff14cc · inbound

Ghost in the Context: Policy-Carriage Integrity in LLM Agents cites this paper.

Ghost in the Context: Policy-Carriage Integrity in LLM Agents LLM Agents Should Employ Security Principles

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:29:12.644850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0d2ef391-5e3f-409c-b30e-6059138001f7 · inbound

Ghost in the Context: Policy-Carriage Integrity in LLM Agents cites this paper.

Ghost in the Context: Policy-Carriage Integrity in LLM Agents LLM Agents Should Employ Security Principles

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-07-03T00:07:27.596565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7c7b7853-fdc2-4fea-8023-43dc2990d156 · inbound

Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI cites this paper.

Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI LLM Agents Should Employ Security Principles

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:26:29.052170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 71e6500c-65af-4abf-8e9d-d28e894d7da6 · inbound

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation cites this paper.

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation LLM Agents Should Employ Security Principles

Reference 244

Resolution: verified exact; arxiv_id, observed 2026-06-27T13:20:57.050204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 90a16c7c-2cd5-4ae4-86c9-ef72ddf6ee7f · inbound

AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming cites this paper.

AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming LLM Agents Should Employ Security Principles

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-07-04T18:00:00.381118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 32bf28b6-f117-4c6b-8aa9-951c366ffe89 · inbound

AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming cites this paper.

AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming LLM Agents Should Employ Security Principles

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-12T12:34:58.460933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8d7d5bb-4367-4626-a82c-7e3f4a68c151 · inbound

Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents cites this paper.

Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents LLM Agents Should Employ Security Principles

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T13:39:51.356324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 58d014e1-8893-40b7-9413-4900eec7ff11 · inbound

Safeguarding LLM Agents from Misalignment through Provenance Analysis cites this paper.

Safeguarding LLM Agents from Misalignment through Provenance Analysis LLM Agents Should Employ Security Principles

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-07-04T01:29:22.001648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2cc1333c-e2fb-42b6-9c5b-f243dd227d9f · inbound

NEXUS: Structured Runtime Safety for Tool-Using LLM Agents cites this paper.

NEXUS: Structured Runtime Safety for Tool-Using LLM Agents LLM Agents Should Employ Security Principles

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T13:11:53.371921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.