Paper Citation Record · LEDGER

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

As of 20 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:2607.13987.

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

pith.paper-citation-record.v1
2607.13987 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T03:09:54.394990Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T14:49:41.241416Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-11T14:49:41.608258Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy0
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 30ddc63f-f447-43b0-8bc8-db7527c4810d · outbound

This paper cites Guyon and A.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Guyon and A

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:53.917558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9aad8ef-51c0-4ad8-91ab-5bb70f749568 · outbound

This paper cites , title =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation , title =

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.007177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52095056-7f70-4e63-8178-5e5fa55a1d5d · outbound

This paper cites an unresolved cited work.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.061130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e3f9fb4-66ce-4b78-bd29-726a14125654 · outbound

This paper cites Proceedings of the 33rd USENIX Security Symposium (USENIX Security) , year =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Proceedings of the 33rd USENIX Security Symposium (USENIX Security) , year =

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.150913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 388101da-b2d8-4c3c-8e68-9124abb3a0bb · outbound

This paper cites Proceedings of the 34th USENIX Security Symposium (USENIX Security) , year =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Proceedings of the 34th USENIX Security Symposium (USENIX Security) , year =

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.189011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9259de3b-2776-4f3a-a675-6817dc4777d3 · outbound

This paper cites Proceedings of the Network and Distributed System Security Symposium (NDSS) , year =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Proceedings of the Network and Distributed System Security Symposium (NDSS) , year =

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.270130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abb8d95e-c764-49fe-b5a2-e2d1c2109961 · outbound

This paper cites Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.333431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ce722e2-5e25-48b1-9c5e-670ac68c29dd · outbound

This paper cites Exploiting LLM Agent Supply Chains via Payload-less Skills.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Exploiting LLM Agent Supply Chains via Payload-less Skills

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.337040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67690c3c-b8db-4c52-b2f0-3443d6458299 · outbound

This paper cites Proceedings of the 17th International Conference on Detection of Intrusions and Malware, and Vulnerability Assessment (DIMVA) , year =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Proceedings of the 17th International Conference on Detection of Intrusions and Malware, and Vulnerability Assessment (DIMVA) , year =

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.339679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9268a0fd-d6dd-4bee-aa51-250df6bf28fb · outbound

This paper cites Proceedings of the 2025 Conference on Applied Machine Learning for Information Security , pages =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Proceedings of the 2025 Conference on Applied Machine Learning for Information Security , pages =

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.341854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5301f39-d432-4ca5-a328-985f9cbe5f89 · outbound

This paper cites SoK: Taxonomy of Attacks on Open-Source Software Supply Chains , year=.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation SoK: Taxonomy of Attacks on Open-Source Software Supply Chains , year=

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.344377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f6d58fa-e1b4-4a3f-8350-2097ac690d16 · outbound

This paper cites and Wan, Sheng and Zhang, Sheng and Lee, Wang-Chien and Sima, Xiaoyuan and Zhao, Siyuan and Wang, Chi , title =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation and Wan, Sheng and Zhang, Sheng and Lee, Wang-Chien and Sima, Xiaoyuan and Zhao, Siyuan and Wang, Chi , title =

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.346647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 172a5431-174e-4adb-9b4a-ddf5cd61d6c5 · outbound

This paper cites and Cao, Yuan , title =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation and Cao, Yuan , title =

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.348820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdabc139-32d9-41a8-89c4-3c5a5b6d6cab · outbound

This paper cites Toolformer: Language Models Can Teach Themselves to Use Tools , booktitle =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Toolformer: Language Models Can Teach Themselves to Use Tools , booktitle =

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.350999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51a23ef0-6532-4acf-bf2a-255e4f8e591f · outbound

This paper cites an unresolved cited work.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.353743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa410b31-30ab-4d70-a298-53c5888041e8 · outbound

This paper cites an unresolved cited work.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.355900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d9708b3-2ca0-4556-8f33-aabd2631319e · outbound

This paper cites an unresolved cited work.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.358022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd5ba0f2-b10e-4120-908e-d542760ddc2c · outbound

This paper cites 34th USENIX Security Symposium (USENIX Security 25) , year =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation 34th USENIX Security Symposium (USENIX Security 25) , year =

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.360478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4809838a-1656-4e00-8094-98a7d0bc50e6 · outbound

This paper cites an unresolved cited work.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.362731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a13136-67f7-4ca9-8012-9867b7ce4a18 · outbound

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

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.365075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fc6fcd8-e73d-462c-b431-4516ccef9b12 · outbound

This paper cites AgentBound: Securing Execution Boundaries of AI Agents , journal =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation AgentBound: Securing Execution Boundaries of AI Agents , journal =

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.367228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0ce20aa-81d0-4eac-aff8-50b791f27d1f · outbound

This paper cites A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.369710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edae0d6f-8007-43b2-abd5-9673688d6321 · outbound

This paper cites Proceedings of the ACM CAIS Workshop on Agent Skills (AgentSkills) , year =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Proceedings of the ACM CAIS Workshop on Agent Skills (AgentSkills) , year =

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.372196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dc4492f-926a-4a0e-b069-6d77ce5c969a · outbound

This paper cites an unresolved cited work.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.374360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0291c510-1360-42f9-8083-ef3ed6123e8f · outbound

This paper cites and Wan, Sheng and Zhang, Sheng and Lee, Wang-Chien and Sima, Xiaoyuan and Zhao, Siyuan and Wang, Chi , title =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation and Wan, Sheng and Zhang, Sheng and Lee, Wang-Chien and Sima, Xiaoyuan and Zhao, Siyuan and Wang, Chi , title =

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.376508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47b03463-4333-4231-8239-36b4056d2825 · outbound

This paper cites Preprints.org , year =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Preprints.org , year =

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.378644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a547c4f5-08ae-495c-850b-d583f85f4441 · outbound

This paper cites SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.380836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81cfdfa0-6348-44c6-84b0-a3cf613ac928 · outbound

This paper cites Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.383286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf821782-25fa-4d9f-9836-4fe903465c3e · outbound

This paper cites Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.385719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99d22276-df8b-4e01-87b5-c84aa00f8381 · outbound

This paper cites "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.388070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c0b8187-cdcb-4538-8358-c484c8e2b10d · outbound

This paper cites and others , title =.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation and others , title =

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.390569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d46f439c-2dfa-4873-86fb-8076c4084063 · outbound

This paper cites an unresolved cited work.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.392806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c6d80cf-0d7f-4e58-aadb-46dc59a7d0d8 · outbound

This paper cites and Chen, Z.

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation and Chen, Z

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T03:09:54.394990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b8a1e26b-bf33-4b59-8aba-1b2a5ba0da0e · inbound

ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization cites this paper.

ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T14:49:41.613414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.