Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-07T16:22:49.737626Z
Paper Citation Record · LEDGER
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
As of 7 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 4 inbound Pith citation observations for arXiv:2604.25109.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-13T17:08:58.831798Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-05T02:28:24.338817Z
Reference resolution
30 of 30 outbound references displayed
- verified exact2
- verified fuzzy12
- unresolved2
- parse uncertain0
- malformed identifier1
- metadata mismatch13
External citation measurements
0
pith, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation 5737b865-a879-4711-9d1b-4ff6ff40d388 · outbound
This paper cites IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T23:46:17.376618Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 79f6427e-6e00-4e95-83c6-99ab758a922c · outbound
This paper cites https: //platform.claude.com/docs/en/agents-and-tools/age nt-skills/overview.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills https: //platform.claude.com/docs/en/agents-and-tools/age nt-skills/overview
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.778293Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3c21ce9a-c500-4ddb-bcc9-9d63d5f651fd · outbound
This paper cites InFindings of the Association for Compu- tational Linguistics: EMNLP 2025, pages 16995– 17006, Suzhou, China.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills InFindings of the Association for Compu- tational Linguistics: EMNLP 2025, pages 16995– 17006, Suzhou, China
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.782248Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 55e757b7-0594-41a7-bd3c-c91ad51ab2f0 · outbound
This paper cites InFindings of the Association for Computational Linguistics: ACL 2025, pages 22134–22173, Vienna, Austria.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills InFindings of the Association for Computational Linguistics: ACL 2025, pages 22134–22173, Vienna, Austria
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.774271Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 377c23ef-e515-45a9-9e0c-cbc3f560a1f6 · outbound
This paper cites SecAlign: Defending Against Prompt Injection with Preference Optimization.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills SecAlign: Defending Against Prompt Injection with Preference Optimization
Reference 5
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T23:46:17.200381Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e8813f0c-bd49-4e29-85fa-f597e57cadda · outbound
This paper cites Context Matters: Repository-Aware Security Analysis of the Agent Skill Ecosystem.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Context Matters: Repository-Aware Security Analysis of the Agent Skill Ecosystem
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-02T03:04:40.367011Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 45a24ff1-390e-4745-bcd9-c3a29d49395a · outbound
This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T23:46:17.015660Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3bcee0ab-1038-4f2e-8f9f-f561b425c34b · outbound
This paper cites SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
Reference 8
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T00:03:05.796937Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 695da77a-7ffb-48a2-af18-e81677200800 · outbound
This paper cites InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models
Reference 9
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T23:46:16.667903Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 625a18d8-649b-426f-a82a-4a0893ef5af0 · outbound
This paper cites Yi Liu, Zhihao Chen, Yanjun Zhang, Gelei Deng, Yuekang Li, Jianting Ning, Ying Zhang, and Leo Yu Zhang.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Yi Liu, Zhihao Chen, Yanjun Zhang, Gelei Deng, Yuekang Li, Jianting Ning, Ying Zhang, and Leo Yu Zhang
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T23:46:14.546734Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 601884f8-022e-43a1-9850-f1983ef65325 · outbound
This paper cites Prompt Injection Attacks and Defenses in LLM-Integrated Applications.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Prompt Injection Attacks and Defenses in LLM-Integrated Applications
Reference 11
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T23:46:16.491119Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b36ad841-d780-41a0-8195-350692e313d5 · outbound
This paper cites https: //huggingface.co/meta-llama/Llama-Prompt-Guard -2-86M.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills https: //huggingface.co/meta-llama/Llama-Prompt-Guard -2-86M
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:40.168298Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8ffc3174-aea7-4fc8-b657-adfbd4b6a118 · outbound
This paper cites an unresolved cited work.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Unresolved cited work
Reference 13
- Resolution
- unresolved
- raw_fallback, observed 2026-05-27T02:18:40.174523Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 092df3b4-d97a-4337-8e1e-0503576f3f3f · outbound
This paper cites InFindings of the Association for Computational Linguistics: NAACL 2025, pages 6499–6524, Albuquerque, New Mexico.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills InFindings of the Association for Computational Linguistics: NAACL 2025, pages 6499–6524, Albuquerque, New Mexico
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.829190Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 791945d7-4c73-4a02-bffa-38bd2fceb317 · outbound
This paper cites https://developers .openai.com/codex/skills.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills https://developers .openai.com/codex/skills
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.805670Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 85cccfbc-7f5e-424a-9a79-d62836e10b1a · outbound
This paper cites Granite Guardian.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Granite Guardian
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T23:46:16.339429Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 639ba8aa-621d-494a-85f5-197c86b6d858 · outbound
This paper cites Accessed: 2026-04-07.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Accessed: 2026-04-07
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.833049Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c72d5386-f4ac-49ba-a328-cb5b5d7e0bc7 · outbound
This paper cites Agent skills enable a new class of realis- tic and trivially simple prompt injections.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Agent skills enable a new class of realis- tic and trivially simple prompt injections
Reference 18
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T23:46:16.750688Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c63b5a28-5968-4ed2-b1d3-4abeb89bf66b · outbound
This paper cites Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
Reference 19
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-16T08:57:26.226663Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 199175be-577e-4662-9df4-148e8d1eb16b · outbound
This paper cites PromptArmor: Simple yet Effective Prompt Injection Defenses.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills PromptArmor: Simple yet Effective Prompt Injection Defenses
Reference 20
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T23:46:16.139929Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 056ac5da-4c01-4e0c-bf21-2e4e74fa6433 · outbound
This paper cites InFindings of the Association for Compu- tational Linguistics: EMNLP 2025, pages 21862– 21880, Suzhou, China.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills InFindings of the Association for Compu- tational Linguistics: EMNLP 2025, pages 21862– 21880, Suzhou, China
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.837421Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 77af8aec-ee96-46a4-8fc4-72aa3cf62f32 · outbound
This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T10:59:30.872595Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 51f94a7a-3c4a-441b-acb5-1032b5cd22da · outbound
This paper cites InFindings of the Association for Computational Linguistics: EMNLP 2025, pages 23159–23172, Suzhou, China.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills InFindings of the Association for Computational Linguistics: EMNLP 2025, pages 23159–23172, Suzhou, China
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.801983Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6eabad03-ec4b-481e-88b8-e39b119bf111 · outbound
This paper cites InFindings of the Association for Computational Linguistics: ACL 2025, pages 13698–13713, Vienna, Austria.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills InFindings of the Association for Computational Linguistics: ACL 2025, pages 13698–13713, Vienna, Austria
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.797660Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5deca162-d313-4484-9760-fe45fbd8fd38 · outbound
This paper cites Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
Reference 25
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T23:46:15.850426Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5fdaa26f-ffc3-4903-9d04-4b51b20c2d69 · outbound
This paper cites InFindings of the Association for Computa- tional Linguistics: NAACL 2025, pages 7116–7132, Albuquerque, New Mexico.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills InFindings of the Association for Computa- tional Linguistics: NAACL 2025, pages 7116–7132, Albuquerque, New Mexico
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.789815Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation db4f2783-725f-4bd5-ad9c-4ccf7d23c9e0 · outbound
This paper cites InFindings of the Association for Computational Linguistics: ACL 2024, pages 10471– 10506, Bangkok, Thailand.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills InFindings of the Association for Computational Linguistics: ACL 2024, pages 10471– 10506, Bangkok, Thailand
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-27T02:18:26.786237Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d9e4af8c-5b1d-4e75-8730-b2691245877b · outbound
This paper cites Agentsentry: Mitigating indirect prompt injection in llm agents via temporal causal diagnostics and context purification.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Agentsentry: Mitigating indirect prompt injection in llm agents via temporal causal diagnostics and context purification
Reference 28
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T23:46:15.539894Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 465a0bbe-2184-4a7b-83df-3a88bfa24246 · outbound
This paper cites an unresolved cited work.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Unresolved cited work
Reference 29
- Resolution
- unresolved
- raw_fallback, observed 2026-05-27T02:18:26.793324Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d7568853-ffeb-4735-9df6-83b1237937d9 · outbound
This paper cites clas- sification over 30 prompts per split.
Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills clas- sification over 30 prompts per split
Reference 30
- Resolution
- malformed identifier
- raw_fallback, observed 2026-05-27T02:18:40.179141Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Pith citing papers
Observation 8284ea6f-eff0-4d40-a6bc-a75d51dab5d8 · inbound
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses cites this paper.
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
Reference 253
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T17:08:58.831798Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 35814a25-28d1-4cde-b4dc-3cf723b2894e · inbound
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries cites this paper.
Skill Drift Is Contract Violation: Proactive Maintenance for LLM Agent Skill Libraries Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T07:32:29.094470Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7ad8c002-69ff-4495-a424-5b52e2b34b71 · inbound
Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems cites this paper.
Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T05:37:19.163897Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8fbd73ff-f309-4253-802c-b6db216c60c9 · inbound
Agent Skill Evaluation and Evolution: Frameworks and Benchmarks cites this paper.
Agent Skill Evaluation and Evolution: Frameworks and Benchmarks Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills
Reference 4
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T05:37:40.299708Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.