github
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the official GitHub CLI (
gh) to perform repository operations such as managing pull requests, triaging issues, and viewing workflow logs. - [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection (Category 8) due to the processing of external repository data.
- Ingestion points: Data from GitHub, including issue descriptions, pull request bodies, and CI log outputs, is ingested into the agent's context through commands like
gh pr view,gh issue list, andgh run view(SKILL.md). - Boundary markers: The instructions do not define delimiters or specific markers to help the agent distinguish between its own instructions and content retrieved from the repository.
- Capability inventory: The agent has access to state-changing commands including
gh pr merge,gh pr create,gh issue close, andgh api(SKILL.md). - Sanitization: There is no evidence of sanitization or validation logic to filter potentially malicious instructions embedded in repository data before processing.
Audit Metadata