fetching-pr-comments

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to fetch and parse Pull Request comments which are external, attacker-controllable data. Malicious actors could place instructions in PR comments to influence the agent's behavior.
  • Ingestion points: External data enters the context via gh api and gh pr view --comments as shown in SKILL.md.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when presenting comment data to the model.
  • Capability inventory: The skill uses gh for read-only operations, but the fetched data could interact with other tools available to the agent.
  • Sanitization: Absent. There is no evidence of filtering or escaping logic for the fetched comment bodies.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:35 PM