address-github-comments

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted external data from GitHub comments.
  • Ingestion points: Comments are fetched using gh pr view --comments in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat fetched comments strictly as data rather than instructions.
  • Capability inventory: The skill possesses the capability to modify the local filesystem (Step 3: 'Apply fixes') and perform network write operations via the GitHub API (gh pr comment).
  • Sanitization: There is no evidence of sanitization or filtering applied to the retrieved comment text.
  • [Command Execution] (SAFE): The skill uses gh CLI commands (auth status, pr view, pr comment) which are appropriate for the stated purpose of managing PR feedback.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:08 PM