Paper Citation Record · LEDGER

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

As of 9 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 24 inbound Pith citation observations for arXiv:2502.08586.

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

pith.paper-citation-record.v1
2502.08586 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T04:37:28.867597Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 24 of 24 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:34:34.815687Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T15:48:35.883148Z

Reference resolution

27 of 27 outbound references displayed

verified exact0
verified fuzzy2
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c7440ac4-45e3-4bb7-a91f-820a2aed8b14 · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.268054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e852125b-d6ff-4489-a04b-a77da23ae6c3 · outbound

This paper cites Tianyu Cui, Yanling Wang, Chuanpu Fu, Yong Xiao, Sijia Li, Xinhao Deng, Yunpeng Liu, Qinglin Zhang, Ziyi Qiu, Peiyang Li, et al.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Tianyu Cui, Yanling Wang, Chuanpu Fu, Yong Xiao, Sijia Li, Xinhao Deng, Yunpeng Liu, Qinglin Zhang, Ziyi Qiu, Peiyang Li, et al

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.368156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9480e77a-efff-4347-abae-590188524f7c · outbound

This paper cites Security and Privacy Challenges of Large Language Models: A Survey.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Security and Privacy Challenges of Large Language Models: A Survey

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.371361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbfe858a-5d44-41c9-b60b-bc90690c4f1b · outbound

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

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.375477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc7e9b01-f2a8-4054-9ba0-f5b095ca68cf · outbound

This paper cites RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.378324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 684061cc-aec2-4e2a-b6d7-3144133a965a · outbound

This paper cites Feng He, Tianqing Zhu, Dayong Ye, Bo Liu, Wanlei Zhou, and Philip S Yu.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Feng He, Tianqing Zhu, Dayong Ye, Bo Liu, Wanlei Zhou, and Philip S Yu

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.385457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98431140-7e89-4d59-ab0a-9a96b91afff6 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.388533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a1455d9-0caa-4766-8dd8-7b9a09263566 · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.391836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1327166-0d8e-46ff-ab58-1c332a735972 · outbound

This paper cites Red Teaming Language Models with Language Models.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Red Teaming Language Models with Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.406491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7334860c-ab06-4cda-ae72-f58a63806e3b · outbound

This paper cites Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.463591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cde1543-df87-4c5d-817a-1cfe0574c2f7 · outbound

This paper cites Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.522854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d2695b8-6189-4fba-a967-dad5b534717a · outbound

This paper cites Language agents achieve superhuman synthesis of scientific knowledge.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Language agents achieve superhuman synthesis of scientific knowledge

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.580674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eda3da75-5be5-4065-9e7c-fa974e876269 · outbound

This paper cites Evil Geniuses: Delving into the Safety of LLM-based Agents.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Evil Geniuses: Delving into the Safety of LLM-based Agents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.636620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d3f6b33-8f2f-4906-9e14-19c0ec4db78b · outbound

This paper cites Data poisoning attacks against federated learn- ing systems.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Data poisoning attacks against federated learn- ing systems

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:37:29.230122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 662ad39e-bce8-4c2a-9cfd-0c3fe35e30f1 · outbound

This paper cites Jiaqi Xue, Mengxin Zheng, Ting Hua, Yilin Shen, Yepeng Liu, Ladislau B¨ol¨oni, and Qian Lou.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Jiaqi Xue, Mengxin Zheng, Ting Hua, Yilin Shen, Yepeng Liu, Ladislau B¨ol¨oni, and Qian Lou

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T04:37:29.220363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1f68dc76-45a4-4ecf-8a2c-213780f94de8 · outbound

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

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.771627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7efd6251-11e5-49d5-8b67-2007d2b53ac3 · outbound

This paper cites The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG).

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.809380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75e283ae-38ba-4953-92f4-67cd737699ad · outbound

This paper cites Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.833682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaaceb16-a8fe-4fb8-8a94-57705e2572ee · outbound

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

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.861187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f195015-f753-4464-a947-6a6c78bc07e5 · outbound

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

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.864419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e82cbe66-f7fa-4f7e-89ff-287c47565931 · outbound

This paper cites PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.867597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d3be1a2-b8fb-4a6e-849c-808561abf87a · outbound

This paper cites AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.364091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b8f9803-dfee-4eb5-832e-dde61e6a10e5 · outbound

This paper cites BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.696356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71d462d9-5a9b-43a1-aea4-39010fe76e3e · outbound

This paper cites A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.381640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c78bb0e7-56c5-4300-8fbf-19f51297f658 · outbound

This paper cites Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.330264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86005911-1a78-45d4-baa8-42fdf1046c33 · outbound

This paper cites ChemCrow: Augmenting large-language models with chemistry tools.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks ChemCrow: Augmenting large-language models with chemistry tools

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.294013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0ddb43a-d175-449f-ae19-ea1f7c0025f3 · outbound

This paper cites Scalable Extraction of Training Data from (Production) Language Models.

Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks Scalable Extraction of Training Data from (Production) Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-08T04:37:28.394855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 253b84ab-1d66-4a3a-9997-cb0a75bd596f · inbound

Large Language Model Agent: A Survey on Methodology, Applications and Challenges cites this paper.

Large Language Model Agent: A Survey on Methodology, Applications and Challenges Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 175

Resolution: verified exact; arxiv_id, observed 2026-05-22T21:52:10.416569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation be51e42f-0e70-476d-9a6d-26463ffa2c86 · inbound

Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services cites this paper.

Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:34:34.815687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4de0b938-f923-4b0a-8e57-4b32cf438f03 · inbound

MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments cites this paper.

MLA-Trust: Benchmarking Trustworthiness of Multimodal LLM Agents in GUI Environments Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:42:33.151323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f9b130e-a6b8-4e84-a6b8-d2fa89e8e789 · inbound

A Red Teaming Roadmap Towards System-Level Safety cites this paper.

A Red Teaming Roadmap Towards System-Level Safety Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T12:11:20.746079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2036883-0a11-4792-ba90-bc10698481e9 · inbound

Levels of Autonomy for AI Agents cites this paper.

Levels of Autonomy for AI Agents Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:52:41.842278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a01d0f6-66ab-4bb4-bdc9-77680eb4f755 · inbound

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems cites this paper.

We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:36.575227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26006061-4145-4732-9dd9-8613a9c4af73 · 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 Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T21:34:41.058806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f34403d8-64b3-4b77-bb38-3907e4f94c74 · inbound

Throttling Web Agents Using Reasoning Gates cites this paper.

Throttling Web Agents Using Reasoning Gates Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-05T12:28:04.262824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f01aec10-85e1-4790-83b8-2ae442ff8fba · inbound

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents cites this paper.

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T08:06:11.330207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f547531-39aa-44f7-bad3-35e3f742389d · inbound

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges cites this paper.

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-18T03:42:22.464757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e36b5551-e79c-4033-9e44-68fbdd28bc08 · inbound

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels cites this paper.

Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T07:06:38.041872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eae352de-994f-46ac-b9b6-3eb072c67fb0 · inbound

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents cites this paper.

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T10:32:31.300703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98b32e61-f9b1-48ef-955d-d23a9baee00c · inbound

Agents at Risk: How Users Unwittingly Undermine LLM Safety cites this paper.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.132433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74e5a25f-89fd-455c-b8cd-06a8e35d706f · inbound

LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning cites this paper.

LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-16T10:57:46.854305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6353e071-8de9-4ae8-bddb-063f71c72e15 · inbound

OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents cites this paper.

OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:56:11.842563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b563fa63-c81c-4092-865f-be3c916bf6c8 · inbound

Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security cites this paper.

Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 99

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:45:01.661562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 28206dc5-9048-4a28-8234-857c0250edde · inbound

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents cites this paper.

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-30T16:24:55.140269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation feca9d20-b067-4135-afa2-fb5e6e604f1d · inbound

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents cites this paper.

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-03T15:48:35.884551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 88883738-429d-418b-9449-9a44d034f077 · inbound

Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare cites this paper.

Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-30T12:44:39.617898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 82e558c9-e23d-48c4-ae91-8a16c5ac1b37 · inbound

Agent Security Needs Redefinition through a Holistic Framework cites this paper.

Agent Security Needs Redefinition through a Holistic Framework Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 268

Resolution: unresolved; no resolver link, observed 2026-08-01T06:04:46.602164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c261576-7405-40f9-bbb1-2588d573b740 · inbound

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs cites this paper.

One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T23:07:37.594638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5d24510-d72f-4e28-a4a8-9a1a0f87e169 · inbound

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents cites this paper.

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T16:36:53.593030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9c7f59c-9fc1-4e6e-b474-ad1fb264f142 · inbound

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents cites this paper.

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:59:39.874950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39a8ec91-4374-48f9-80f7-73e24dbbf8c2 · inbound

Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure cites this paper.

Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-05T00:54:57.371881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.