pr-comments-address
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from GitHub PR comments and project-level rules files which could contain malicious instructions.
- Ingestion points: External content is fetched via 'gh pr view' (comments) and local file reads (CLAUDE.md/rules).
- Boundary markers: Instructions do not use delimiters or provide warnings to ignore embedded instructions in external data.
- Capability inventory: The skill has the ability to write to the file system and perform authenticated GitHub API writes.
- Sanitization: No programmatic sanitization or validation of comment content is performed.
- [SAFE]: The skill explicitly includes mandatory human-in-the-loop (HITL) checkpoints in Step 4, Step 5, and Step 8, requiring explicit user approval before the agent modifies files or posts replies to GitHub.
Audit Metadata