deliver
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from sources like bug descriptions, issues, and PR comments which could contain adversarial instructions. \n
- Ingestion points: Processes user-controlled text from issues and pull requests (SKILL.md). \n
- Boundary markers: No delimiters or protective instructions are specified to isolate untrusted content. \n
- Capability inventory: Can perform Git merges, branch deletions, and trigger code modifications through other skills like /implement (SKILL.md). \n
- Sanitization: No evidence of input validation or escaping for the ingested data.
Audit Metadata