Paper Citation Record · LEDGER

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

As of 20 July 2026, this Paper Citation Record lists 0 of 0 outbound references and 36 inbound Pith citation observations for arXiv:2602.06547.

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

pith.paper-citation-record.v1
2602.06547 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-20T06:30:07.809122+00:00

measured 36 of 36 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T18:32:00.165926Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T12:15:01.137692Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation a58f194b-62ff-4ebc-858c-6988fbf58af0 · inbound

Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward cites this paper.

Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 34

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 2026-07-20T06:30:07.809122+00:00.

Observation b7b1f02b-cd7b-4065-b006-75b348508021 · inbound

Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis cites this paper.

Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 10

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 2026-07-20T06:30:07.809122+00:00.

Observation d8563bdd-cc57-489a-87ac-5475b525cb47 · inbound

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study cites this paper.

How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 31

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 2026-07-20T06:30:07.809122+00:00.

Observation 8c2b7cc8-c607-4992-ae16-db14cae7537c · inbound

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement cites this paper.

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T11:36:41.748710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18c7c13b-88f8-40f2-8c25-2b97d23b1560 · inbound

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills cites this paper.

SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 7

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 2026-07-20T06:30:07.809122+00:00.

Observation 6a59a751-d8b6-4d2f-9818-7cc08b2c1cd0 · inbound

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents? cites this paper.

HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents? "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 40

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 2026-07-20T06:30:07.809122+00:00.

Observation e26c3783-11d3-4f57-9f0f-f0204cbed645 · inbound

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents cites this paper.

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 7

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 2026-07-20T06:30:07.809122+00:00.

Observation d6771a2f-59b0-451c-9ce0-0b488814b3f6 · inbound

Sealing the Audit-Runtime Gap for LLM Skills cites this paper.

Sealing the Audit-Runtime Gap for LLM Skills "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 28

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 2026-07-20T06:30:07.809122+00:00.

Observation 4d053c6c-0670-4cfd-94e1-118f39b3d9c8 · inbound

SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills cites this paper.

SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 30

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 2026-07-20T06:30:07.809122+00:00.

Observation 04aa8c47-efe3-4a5c-af7d-59ec189db109 · inbound

Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills cites this paper.

Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 19

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 2026-07-20T06:30:07.809122+00:00.

Observation 3645a3d2-973a-4149-bec7-977bc78ad780 · inbound

Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry cites this paper.

Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 6

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 2026-07-20T06:30:07.809122+00:00.

Observation 453a9e38-3b37-4cf5-8d1f-4c6aaf8695c9 · inbound

Behavioral Integrity Verification for AI Agent Skills cites this paper.

Behavioral Integrity Verification for AI Agent Skills "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 45

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 2026-07-20T06:30:07.809122+00:00.

Observation a35fd265-d209-4341-a9c2-2ae35a90ae9f · inbound

Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems cites this paper.

Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 19

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 2026-07-20T06:30:07.809122+00:00.

Observation 023291e2-613d-4f9c-94e5-b860258c8860 · inbound

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces cites this paper.

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 68

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 2026-07-20T06:30:07.809122+00:00.

Observation 35320b10-9519-42ee-bfcb-729f4a223aa9 · inbound

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces cites this paper.

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:55:46.260903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 1ffa2fd1-5fbe-4c14-97e3-dbaf2732cb35 · inbound

Do Skill Descriptions Tell the Truth? Detecting Undisclosed Security Behaviors in Code-Backed LLM Skills cites this paper.

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 2026-07-20T06:30:07.809122+00:00.

Observation 256e5e61-b23a-4ab0-93bd-8f2bf8adcd04 · inbound

No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills cites this paper.

No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 40

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 2026-07-20T06:30:07.809122+00:00.

Observation 2f3d1fd8-5433-4652-9a0f-4cd3fb39dbcb · inbound

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

Exploiting LLM Agent Supply Chains via Payload-less Skills "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 18

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 2026-07-20T06:30:07.809122+00:00.

Observation 83313865-fb10-43f8-98cc-4a1320d016f9 · inbound

Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network cites this paper.

Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-06-29T22:04:00.804468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation a356c249-de47-4030-99ed-e0290226c919 · inbound

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems cites this paper.

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:52:36.063918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation ceeac290-df12-4b55-b12b-702b4d41d882 · inbound

Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems cites this paper.

Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-06-28T20:52:38.049567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 1ef6e64b-60e2-439b-9407-dfea3057c1ee · inbound

ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree cites this paper.

ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-07-01T21:36:15.869880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 2319c9c9-9741-4a8e-8dce-3d45c4166710 · inbound

SkillGuard: A Permission-Centric Framework for Agent Skill Security cites this paper.

SkillGuard: A Permission-Centric Framework for Agent Skill Security "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-02T03:26:28.571131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation a8a574c9-8103-4c40-8438-0549e96ef8b0 · inbound

SkillGuard: A Permission-Centric Framework for Agent Skill Security cites this paper.

SkillGuard: A Permission-Centric Framework for Agent Skill Security "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-14T18:32:00.165926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efeda93e-bfb9-4912-a49a-f41453fce5bf · inbound

Pomona: Continuous Code Quality Improvement via Small, Automated Changes at Bloomberg cites this paper.

Pomona: Continuous Code Quality Improvement via Small, Automated Changes at Bloomberg "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-02T15:17:08.552037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 3350496f-7954-4879-9618-b2be3e2e83ca · inbound

POISE: Position-Aware Undetectable Skill Injection on LLM Agents cites this paper.

POISE: Position-Aware Undetectable Skill Injection on LLM Agents "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T21:17:24.374971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation b0f66505-3eb4-461f-8b53-763e3bcef5e3 · inbound

Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security cites this paper.

Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-06-27T09:30:46.564685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 6bf461e4-fbbf-47c7-8bf2-db35a2d62685 · inbound

Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents cites this paper.

Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T22:42:46.505972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation cc3aff4e-b399-4d81-9615-9d9ff311a71f · inbound

Detecting Malicious Agent Skills in the Wild using Attention cites this paper.

Detecting Malicious Agent Skills in the Wild using Attention "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-04T11:39:47.671771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 73fbd213-8401-4e25-884e-bb93f12a06d9 · inbound

VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills cites this paper.

VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 61

Resolution: verified exact; local_arxiv, observed 2026-07-04T13:59:52.313720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 675d95b6-020e-459e-9bd8-b479b1e0b3c7 · inbound

The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills cites this paper.

The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T10:15:44.196758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 61a0d135-1567-42f1-a6cd-9b89bfc0cdee · inbound

Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains cites this paper.

Skills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chains "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T08:16:47.228585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation b1bce892-5edb-4ede-b1b4-60ded498f15f · inbound

AgentFlow: Building Agent Dependency Graphs for Static Analysis of Agent Programs cites this paper.

AgentFlow: Building Agent Dependency Graphs for Static Analysis of Agent Programs "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-03T09:17:47.637150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation cc55a830-2959-4781-bee5-6b4d2f0e413e · inbound

Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware cites this paper.

Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T10:37:56.195132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-20T06:30:07.809122+00:00.

Observation 758df83d-6c09-4ae2-a1dd-098148241299 · inbound

Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware cites this paper.

Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T08:09:57.596812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e01bbb17-9627-4dad-ba37-e7275b9e165b · inbound

Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach cites this paper.

Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-14T11:00:53.732771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.