github
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub (issue titles, pull request content, and CI/CD logs), which represents a potential attack surface for indirect instructions.
- Ingestion points: Data is pulled from external GitHub repositories via
gh api,gh issue list, andgh run viewas shown inSKILL.md. - Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore embedded instructions within the fetched content.
- Capability inventory: The skill performs read-only and state-querying operations using the
ghCLI. - Sanitization: No specific sanitization or filtering logic is defined for the external output before it is processed by the agent context.
Audit Metadata