merge-pr
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external GitHub PRs and issues which could contain malicious instructions.
- Ingestion points: PR descriptions and issue bodies (referenced in Rule 2 and Rule 3).
- Boundary markers: None present to distinguish between instructions and data.
- Capability inventory: GitHub PR merging, issue closing, issue body modification, and branch deletion.
- Sanitization: No evidence of sanitization or validation of the content read from GitHub.
Audit Metadata