Paper Citation Record · LEDGER

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

As of 21 August 2026, this Paper Citation Record lists 8 of 8 outbound references and 3 inbound Pith citation observations for arXiv:2605.28588.

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

pith.paper-citation-record.v1
2605.28588 v1

Coverage vector

measured 8 of 8 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T11:51:14.939425Z

measured 11 of 11 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 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T11:52:15.910115Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T06:59:37.263500Z

Reference resolution

8 of 8 outbound references displayed

verified exact1
verified fuzzy0
unresolved7
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2f0aa0dc-27a0-4ff0-8f48-a8607fd05791 · outbound

This paper cites toxic flows,.

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem toxic flows,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-29T11:51:14.939425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88165b43-c856-418d-8cbf-0d899a8d2264 · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection.

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T11:51:14.939425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a5d0f70-1337-4666-9d13-1d9a6d451442 · outbound

This paper cites Github mcp exploited: Accessing private repositories via mcp.

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem Github mcp exploited: Accessing private repositories via mcp

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T11:51:14.939425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2fc3971-a034-4454-9f46-17508c8757ca · outbound

This paper cites Clawdbot skills ganked your crypto.

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem Clawdbot skills ganked your crypto

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-29T11:51:14.939425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 851a70e4-26ae-49b1-88fc-ab6c3a789668 · outbound

This paper cites Superhuman AI exfiltrates emails.

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem Superhuman AI exfiltrates emails

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T11:51:14.939425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ad1ae7f-ed32-417b-9cca-bfd2310c9a1c · outbound

This paper cites Agent skills enable a new class of realis- tic and trivially simple prompt injections.

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem Agent skills enable a new class of realis- tic and trivially simple prompt injections

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-29T11:53:23.635900Z

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.

Observation a0369966-f29a-48b6-b32b-833a4f1e8c7a · outbound

This paper cites Inside the ‘clawdhub’ malicious campaign: AI agent skills drop reverse shells on OpenClaw marketplace.

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem Inside the ‘clawdhub’ malicious campaign: AI agent skills drop reverse shells on OpenClaw marketplace

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T11:51:14.939425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 936ddadc-bbca-4e7f-bf7c-43fb7e50032f · outbound

This paper cites The lethal trifecta.

Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem The lethal trifecta

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T11:51:14.939425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 06f3f556-c465-4de3-815a-6e0984d5ca83 · inbound

SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents cites this paper.

SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-01T00:35:10.388567Z

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.

Observation 09f56075-0c82-46aa-b636-b10c44a023ef · inbound

Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime Layer cites this paper.

Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime Layer Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-04T06:59:37.264746Z

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.

Observation bd4e4399-af3e-4b85-9657-72d139a677c4 · inbound

ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners cites this paper.

ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-11T11:52:15.910115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.