get-pr-comments

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-generated data from pull request review and discussion comments, which could contain malicious instructions designed to influence the agent.
  • Ingestion points: User comments and discussion threads from the active pull request as defined in SKILL.md.
  • Boundary markers: There are no delimiters or instructions to ignore potential commands within the fetched content.
  • Capability inventory: The skill focuses on summarization and action list generation; it does not explicitly request file system or network execution privileges.
  • Sanitization: No sanitization or validation of the external comment data is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 04:28 PM
Security Audit — agent-trust-hub — get-pr-comments