github
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external GitHub repositories, which creates a potential surface for indirect prompt injection via untrusted repository content.
- Ingestion points: The skill uses commands like
gh pr checks,gh run view, andgh apito fetch data from GitHub, which could include attacker-controlled text in PR titles, logs, or issue descriptions. - Boundary markers: The instructions do not define specific boundary markers or 'ignore' directives to help the agent distinguish between skill instructions and the data retrieved from GitHub.
- Capability inventory: The skill relies on the
ghCLI for network communication and repository management, which are standard capabilities for this use case. - Sanitization: There is no evidence of explicit sanitization or filtering of the content returned by the GitHub API before it is processed by the agent.
Audit Metadata