Paper Citation Record · LEDGER

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

As of 5 August 2026, this Paper Citation Record lists 6 of 6 outbound references and 17 inbound Pith citation observations for arXiv:2604.04989.

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

pith.paper-citation-record.v1
2604.04989 v1

Coverage vector

measured 6 of 6 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-13T11:36:41.748710Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 17 of 17 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T23:56:14.830929Z

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

6 of 6 outbound references displayed

verified exact0
verified fuzzy0
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 68d0c596-8ca5-4d73-acc1-199a8883a74e · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 1

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 46f0b412-409f-4e5f-a34d-94fe5e00d6c6 · outbound

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

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents

Reference 2

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 8c2b7cc8-c607-4992-ae16-db14cae7537c · outbound

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

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 e1ad0971-5f5b-48d5-82ee-d8c75477919f · outbound

This paper cites Red Teaming Language Models with Language Models.

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement Red Teaming Language Models with Language Models

Reference 4

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 744aa45f-9d21-4b35-9a20-6ee0f1d57e79 · outbound

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

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement Prompt Injection Attack to Tool Selection in LLM Agents

Reference 5

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 d2f6e009-fa7a-4f8f-b378-29afc43db615 · outbound

This paper cites R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Reference 6

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

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 552b4372-40e0-42ac-97e6-ce1c994f383c · inbound

From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills cites this paper.

From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 2

Resolution: malformed identifier; local_arxiv, observed 2026-05-11T21:51:23.948379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b1275cf9-9219-42c2-92f3-cd4f9b6ea61e · inbound

From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills cites this paper.

From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-05-09T00:14:27.110068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2b3321d3-5ba2-446e-87a1-4bfc9e6de600 · inbound

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

SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-11T20:21:08.933343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ef609f95-b9ed-4c5e-9869-55039184eff6 · inbound

On the dilaton gravity of analogue black holes cites this paper.

On the dilaton gravity of analogue black holes SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T17:06:32.429160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4be056bf-d48f-4a73-938e-7458d355732b · inbound

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw cites this paper.

Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-13T00:57:00.679223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bcf3304f-c08a-470c-8b00-74353f640417 · inbound

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

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:12:17.949635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cbcfb3c6-5914-4031-bc61-55fe07c6f74a · inbound

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

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:55:46.274461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e115d89f-9496-4632-8979-1df647675173 · inbound

Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents cites this paper.

Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-22T03:51:02.021179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0e5c6822-d251-4ce3-9541-a883f6433b3d · inbound

Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents cites this paper.

Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-30T16:14:53.518577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 724d8a1b-a9e1-4cd9-86da-f84a3e2ca6dc · inbound

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction cites this paper.

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 47

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T22:46:19.938612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 89e4173c-b014-4b51-9c52-910367057f5c · inbound

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

POISE: Position-Aware Undetectable Skill Injection on LLM Agents SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T21:17:24.388654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f1b962d7-0874-419f-8c1f-48949fb2c7cf · inbound

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

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-06-27T13:20:56.713011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a8eb1ac5-5c03-4cdd-bd21-3248354877e0 · inbound

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

Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-06-27T09:30:46.539515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 32cbb245-3e4f-4815-82c6-432dc79572a3 · 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 SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-07-02T08:16:47.231239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a90599da-1cd8-476b-b2a2-16da1ef1f99a · inbound

CONTRA: Red-Teaming Configurations of Personalizable Agents cites this paper.

CONTRA: Red-Teaming Configurations of Personalizable Agents SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-12T04:03:40.067404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ff8298d-d546-41cd-be8c-5a8c5754b3f6 · inbound

Skillsets on the Chain: A Blockchain-based Zero-Trust Framework for Agentic AI Networking cites this paper.

Skillsets on the Chain: A Blockchain-based Zero-Trust Framework for Agentic AI Networking SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T01:22:31.310223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4709215b-7444-4788-ba22-669a2a63051b · inbound

RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection cites this paper.

RING: Retrieval-Internalized Generation for Continual Large-Scale Knowledge Injection SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T23:56:14.830929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.