Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-14T19:06:00.332789Z
Paper Citation Record · LEDGER
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills
As of 6 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2605.12875.
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
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
31 of 31 outbound references displayed
- verified exact13
- verified fuzzy16
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation ea8747ce-f509-4e69-b346-698500336395 · outbound
This paper cites Extend claude with skills.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Extend claude with skills
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.700344Z
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 138526ca-9999-4f28-a5c1-66c355c2e562 · outbound
This paper cites About agent skills.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills About agent skills
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.680325Z
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 f2df76fb-3e86-4e5b-89b6-9ade7c7aa191 · outbound
This paper cites SkillsinChatGPT.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills SkillsinChatGPT
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T19:07:51.273282Z
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 8b95f619-7fb6-489e-932b-82dc354135a9 · outbound
This paper cites Creating agent skills for github copilot.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Creating agent skills for github copilot
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.687096Z
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 f9da43ab-ab23-43bb-a523-8c0e3e06b486 · outbound
This paper cites Claude code overview.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Claude code overview
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.689211Z
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 196101b7-cfb3-4efa-9035-62ecf29cbc10 · outbound
This paper cites Security.
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.695977Z
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 7e7cacf5-bc93-432f-a408-9c110bde6b72 · outbound
This paper cites Adding agent skills for github copilot cli.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Adding agent skills for github copilot cli
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.672900Z
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 9c2da38f-a04a-4a0b-a7b7-be602f14a997 · outbound
This paper cites Skillsmp: Agent skills marketplace.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Skillsmp: Agent skills marketplace
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.684749Z
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 0bdf75cf-40a3-41f1-8f2e-6ea50718963a · outbound
This paper cites Agent skills library.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Agent skills library
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.677946Z
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 d3ddacb1-a7d4-4372-af7e-ec80d5877cf8 · outbound
This paper cites Modeling and discovering vulnerabilities with code property graphs.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Modeling and discovering vulnerabilities with code property graphs
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.675672Z
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 9715ac7e-533b-43cd-ad05-61d6f9e11271 · outbound
This paper cites Overview | joern documentation.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Overview | joern documentation
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.682765Z
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 cd394c1a-a730-4c2e-bb04-da4c63f70705 · outbound
This paper cites Small world with high risks: A study of security threats in the npm ecosystem.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Small world with high risks: A study of security threats in the npm ecosystem
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.691736Z
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 9287908d-20d1-45e9-9aa8-fce9c6b359d8 · outbound
This paper cites Towards Measuring Supply Chain Attacks on Package Managers for Interpreted Languages.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Towards Measuring Supply Chain Attacks on Package Managers for Interpreted Languages
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T19:07:51.255301Z
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 fdcc67e0-ff38-4b41-82e6-f398a10945ad · outbound
This paper cites Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T23:41:24.390564Z
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 1ffa2fd1-5fbe-4c14-97e3-dbaf2732cb35 · outbound
This paper cites "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-06-02T04:04:28.114733Z
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 403a1b30-81e2-49c0-84ff-58fe1380e054 · outbound
This paper cites Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
Reference 16
- Resolution
- verified exact
- 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 fe472029-98f3-4b50-a530-e7b40c66d9f9 · outbound
This paper cites When skills lie: Hidden-comment injection in llm agents.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills When skills lie: Hidden-comment injection in llm agents
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T19:07:51.249476Z
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 de7ed85e-2e21-423d-8e3a-1512fd59bf5c · outbound
This paper cites Model context protocol (mcp): Landscape, security threats, and future research directions.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Model context protocol (mcp): Landscape, security threats, and future research directions
Reference 18
- Resolution
- verified exact
- doi, observed 2026-05-14T19:07:50.139506Z
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 ebea81e4-ea98-4484-ac9e-ef099ed188c4 · outbound
This paper cites Mcptox: A benchmark for tool poisoning on real-world mcp servers.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Mcptox: A benchmark for tool poisoning on real-world mcp servers
Reference 19
- Resolution
- verified exact
- doi, observed 2026-05-14T19:07:50.157578Z
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 057f16a0-3336-4a40-874e-d4f01cba6f87 · outbound
This paper cites Agent audit: A security analysis system for llm agent applications.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Agent audit: A security analysis system for llm agent applications
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T19:07:51.261400Z
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 fcc755d9-f88f-4032-b57f-c653b20fc7ab · outbound
This paper cites Agentsentinel: An end-to-end and real-time security defense framework for computer-use agents.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Agentsentinel: An end-to-end and real-time security defense framework for computer-use agents
Reference 21
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-14T19:07:50.145818Z
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 f1efcaea-efa8-4801-86ee-46f1d2eb343e · outbound
This paper cites A contemporary survey of large language model assisted program analysis.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills A contemporary survey of large language model assisted program analysis
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-14T19:07:50.152927Z
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 ec11fbbd-283a-41df-9c7a-378b96989839 · outbound
This paper cites Large language model for vulnerability detection and repair: Literature review and the road ahead.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Large language model for vulnerability detection and repair: Literature review and the road ahead
Reference 23
- Resolution
- verified exact
- doi, observed 2026-05-14T19:07:50.162002Z
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 0c489996-2647-4d31-917a-f57c6fbe1ad1 · outbound
This paper cites Can LLM Prompting Serve as a Proxy for Static Analysis in Vulnerability Detection.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Can LLM Prompting Serve as a Proxy for Static Analysis in Vulnerability Detection
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T19:07:51.305289Z
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 d8e00960-7e72-4cdd-9913-73544c0f408b · outbound
This paper cites Large language models versus static code analysis tools: A systematic benchmark for vulnerability detection.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Large language models versus static code analysis tools: A systematic benchmark for vulnerability detection
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.693989Z
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 cb27750f-b577-413d-8fef-ad058d75cda5 · outbound
This paper cites Iris: Llm-assisted static analysis for detecting security vulnerabilities.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Iris: Llm-assisted static analysis for detecting security vulnerabilities
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.670302Z
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 96731b9e-69e7-4d6b-a73f-7ded4205bd35 · outbound
This paper cites Minimizing False Positives in Static Bug Detection via LLM-Enhanced Path Feasibility Analysis.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Minimizing False Positives in Static Bug Detection via LLM-Enhanced Path Feasibility Analysis
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T19:07:51.298705Z
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 b5f87010-602e-4f56-991d-f7faeef24fca · outbound
This paper cites Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns
Reference 28
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T19:07:51.292380Z
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 e4073034-7432-4b62-af97-6c29d1aa9bec · outbound
This paper cites A large-scale empirical study on code-comment inconsistencies.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills A large-scale empirical study on code-comment inconsistencies
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.666235Z
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 bceb8314-023f-401e-bf17-b4c01d342807 · outbound
This paper cites Deep just- in-time inconsistency detection between comments and source code.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Deep just- in-time inconsistency detection between comments and source code
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.698419Z
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 395e93bd-68b7-40e2-bd3f-e62db61dc1b4 · outbound
This paper cites Docchecker: Bootstrapping code large language model for detecting and resolving code-comment inconsistencies.
Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills Docchecker: Bootstrapping code large language model for detecting and resolving code-comment inconsistencies
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-15T21:01:39.668282Z
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
No inbound Pith citation observations are available.