Paper Citation Record · LEDGER

Agents at Risk: How Users Unwittingly Undermine LLM Safety

As of 9 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 2 inbound Pith citation observations for arXiv:2601.10758.

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

pith.paper-citation-record.v1
2601.10758 v3

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T10:45:20.111398Z

measured 42 of 42 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T15:17:29.479184Z

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

40 of 40 outbound references displayed

verified exact0
verified fuzzy0
unresolved40
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation e432f370-e493-4995-89d7-62900a34e679 · outbound

This paper cites Security and Privacy4(4), e159 (2021).

Agents at Risk: How Users Unwittingly Undermine LLM Safety Security and Privacy4(4), e159 (2021)

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:15.835365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35ecfa6f-2d8d-489f-ac22-73d674ff82be · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Constitutional AI: Harmlessness from AI Feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:15.947776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d11f8b85-1555-4fa0-8c3b-44052593c3c5 · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:16.101607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9098b25-c8b6-4072-945e-51c76cf128f6 · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:16.246142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51fba39d-55d5-47d6-96f6-8093a40e103f · outbound

This paper cites In: 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML).

Agents at Risk: How Users Unwittingly Undermine LLM Safety In: 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:16.407118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b057cb23-5b13-48f2-a92e-f60277d028c0 · outbound

This paper cites Advances in Neural Information Processing Systems37, 26814–26845 (2024).

Agents at Risk: How Users Unwittingly Undermine LLM Safety Advances in Neural Information Processing Systems37, 26814–26845 (2024)

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:16.550874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc184c0e-2ad2-43d0-bde6-2e5ec1866066 · outbound

This paper cites GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents.

Agents at Risk: How Users Unwittingly Undermine LLM Safety GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:16.759066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b20850-bce2-4faa-bcba-f59675a3a9be · outbound

This paper cites In: 2025 IEEE Symposium on Security and Privacy (SP).

Agents at Risk: How Users Unwittingly Undermine LLM Safety In: 2025 IEEE Symposium on Security and Privacy (SP)

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:16.981213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ce0185b-63fe-4ab0-9523-f66284bf8351 · outbound

This paper cites International Journal of Human-Computer Studies125, 19–31 (2019).

Agents at Risk: How Users Unwittingly Undermine LLM Safety International Journal of Human-Computer Studies125, 19–31 (2019)

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:17.147032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62d9e10d-e54b-47f5-a2cd-8d29de7c77ee · outbound

This paper cites In: Proceedings of the 16th ACM workshop on artificial intelligence and security.

Agents at Risk: How Users Unwittingly Undermine LLM Safety In: Proceedings of the 16th ACM workshop on artificial intelligence and security

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:17.356157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f916113-a364-42c3-acfc-359bd3e7e16d · outbound

This paper cites Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:17.529100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f4a2ed6-0dcf-41d9-9ffd-5b9939ece92d · outbound

This paper cites Large Language Model based Multi-Agents: A Survey of Progress and Challenges.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Large Language Model based Multi-Agents: A Survey of Progress and Challenges

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:17.794251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 098376b3-d861-4325-b755-dd84821aa5df · outbound

This paper cites In: 33rd USENIX Security Symposium (USENIX Security 24).

Agents at Risk: How Users Unwittingly Undermine LLM Safety In: 33rd USENIX Security Symposium (USENIX Security 24)

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:17.903004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6761f49-a15c-48c6-a9b5-fa50afade2dc · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:17.956036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6639fb5e-9397-4c43-9cbe-61c203c042ab · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.009539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b0cef02-5cca-4e62-91f4-373d8fbbdd1f · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.080741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks.

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 6c061f65-f33d-4717-992c-7a16f85f5a6a · outbound

This paper cites EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage.

Agents at Risk: How Users Unwittingly Undermine LLM Safety EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.184723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 058bcab8-04cb-4988-b4dd-dcaf3433752d · outbound

This paper cites preferences.

Agents at Risk: How Users Unwittingly Undermine LLM Safety preferences

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.264083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46489787-664c-4291-8fdb-c4afd4efd556 · outbound

This paper cites In: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems.

Agents at Risk: How Users Unwittingly Undermine LLM Safety In: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.320221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dc61b19-8dca-453a-862e-d1edeeb5e11c · outbound

This paper cites LASER: LLM Agent with State-Space Exploration for Web Navigation.

Agents at Risk: How Users Unwittingly Undermine LLM Safety LASER: LLM Agent with State-Space Exploration for Web Navigation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.400841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9a8b1f2-b393-4d16-b0f8-34ebea8da355 · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.511551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 361e6f4e-b69f-43c8-97c5-4fe7c2bf7f9e · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.587713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3da10df-f534-48ab-a0ad-50638d088d1a · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.670577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 597deca6-de6f-47f0-830b-c83d15f3a3d3 · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.726697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f75cb55-b457-4355-98b0-7f1fa8ccec48 · outbound

This paper cites Prompt Injection Attack to Tool Selection in LLM Agents.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Prompt Injection Attack to Tool Selection in LLM Agents

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.810302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0472dc87-c557-4a6e-9bd9-00eb3079e021 · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.863024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f96b43a-9645-4d10-a587-a55a8a268b3b · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:18.916271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d814c3da-89c8-4c9b-9f9f-e3d0789e16b1 · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.042225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e811ab58-647b-4606-a2f9-ae50bb07fdb3 · outbound

This paper cites an unresolved cited work.

Agents at Risk: How Users Unwittingly Undermine LLM Safety Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.160989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8401c4a0-3dfa-42a8-a3f8-cf7fb49d5618 · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

Agents at Risk: How Users Unwittingly Undermine LLM Safety The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.283817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd74da55-4d1c-4d56-b1a3-9cbab589d6fb · outbound

This paper cites arXiv e-prints pp.

Agents at Risk: How Users Unwittingly Undermine LLM Safety arXiv e-prints pp

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.434987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c7bc88a-7877-42e1-aa37-ab93341389eb · outbound

This paper cites arXiv preprint arXiv:2510.19207 (2025).

Agents at Risk: How Users Unwittingly Undermine LLM Safety arXiv preprint arXiv:2510.19207 (2025)

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.491402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57c7835c-cd00-4931-b37f-e1bede23007f · outbound

This paper cites In: NDSS (2025).

Agents at Risk: How Users Unwittingly Undermine LLM Safety In: NDSS (2025)

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.562067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b149cb52-69c8-4166-9817-38d256c2f88f · outbound

This paper cites AdvAgent: Controllable Blackbox Red-teaming on Web Agents.

Agents at Risk: How Users Unwittingly Undermine LLM Safety AdvAgent: Controllable Blackbox Red-teaming on Web Agents

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.642964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc236d1a-094c-4300-ab84-70e0ffb8542c · outbound

This paper cites BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models.

Agents at Risk: How Users Unwittingly Undermine LLM Safety BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.715096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e346707-b1c3-48ab-809d-c875c1760100 · outbound

This paper cites In: Companion Proceed- ings of the 32nd ACM International Conference on the Foundations of Software Engineering.

Agents at Risk: How Users Unwittingly Undermine LLM Safety In: Companion Proceed- ings of the 32nd ACM International Conference on the Foundations of Software Engineering

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.729446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4b7f5e4-10c7-4788-bf5b-7202886e1e6b · outbound

This paper cites In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers).

Agents at Risk: How Users Unwittingly Undermine LLM Safety In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.808251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06375c20-1ee5-4c50-981b-d6730bdeb901 · outbound

This paper cites IEEE Transactions on Dependable and Secure Computing21(6), 5242–5258 (2024).

Agents at Risk: How Users Unwittingly Undermine LLM Safety IEEE Transactions on Dependable and Secure Computing21(6), 5242–5258 (2024)

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:19.950155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6a0271f-1b66-4b1f-afef-b937aaeeb5af · outbound

This paper cites In: 34th USENIX Security Symposium (USENIX Security 25).

Agents at Risk: How Users Unwittingly Undermine LLM Safety In: 34th USENIX Security Symposium (USENIX Security 25)

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T10:45:20.111398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a2dc1e2f-60d3-43db-afbf-9d19f0fdb259 · inbound

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

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation Agents at Risk: How Users Unwittingly Undermine LLM Safety

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-07T03:18:52.400858Z

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 434c2944-cfc8-4d31-83f4-cebc5b6a34f8 · inbound

PlanFlip: Attacking Multi-Agent LLM Systems via Planning-Phase Prompt Injection cites this paper.

PlanFlip: Attacking Multi-Agent LLM Systems via Planning-Phase Prompt Injection Agents at Risk: How Users Unwittingly Undermine LLM Safety

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T15:17:29.479184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.