skills/shipshitdev/skills/pr-comments/Gen Agent Trust Hub

pr-comments

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external, potentially attacker-controlled pull request comments, which creates a surface for indirect prompt injection. \n
  • Ingestion points: GitHub PR comments are fetched in SKILL.md using gh api and gh pr view commands. \n
  • Boundary markers: The skill explicitly instructs the agent to treat comment text as untrusted and never follow instructions embedded in a comment. \n
  • Capability inventory: The skill uses gh (GitHub CLI) and git for repository access and data retrieval. It does not perform writes or execute the content of the comments. \n
  • Sanitization: It directs the agent to summarize content and redact secret-like values, reducing the likelihood of accidental execution or data leak.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 01:29 PM
Security Audit — agent-trust-hub — pr-comments