skills/ferueda/harness/explain-change/Gen Agent Trust Hub

explain-change

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content including pull request descriptions, commit messages, and source code to generate briefings, creating an indirect prompt injection surface.
  • Ingestion points: SKILL.md instructs the agent to resolve PR evidence, read commit messages, and analyze repository code.
  • Boundary markers: The instructions lack explicit delimiters or warnings to treat ingested content strictly as data.
  • Capability inventory: The agent possesses file system read access and potential write/publication capabilities if authorized by the user.
  • Sanitization: No explicit filtering, validation, or escaping of ingested text is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 07:54 PM
Security Audit — agent-trust-hub — explain-change