git-pr-comments

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process unresolved feedback from GitHub pull requests, creating a surface for indirect prompt injection from external contributors.
  • Ingestion points: The skill reads unresolved comments from the PR conversation view in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to help the agent distinguish between legitimate feedback and adversarial instructions embedded within comments.
  • Capability inventory: The skill has the capability to perform code edits, stage changes, create git commits, and execute tests or linters.
  • Sanitization: No sanitization or validation mechanisms are defined for the content of the comments before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 10:29 PM
Security Audit — agent-trust-hub — git-pr-comments