review-pr-thread-verify
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external contributors in pull requests, which could contain malicious instructions.
- Ingestion points: The skill receives author replies, commit messages, and the full PR history as context for its decision-making.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested PR data.
- Capability inventory: The skill has no tools or executable capabilities; it only returns a structured disposition to the caller.
- Sanitization: There is no mention of sanitizing or filtering the PR content before analysis.
- [NO_CODE]: The skill consists entirely of markdown instructions and YAML metadata without any accompanying scripts or executable files.
Audit Metadata