pr
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Employs git and the GitHub CLI (gh) to perform repository actions such as viewing diffs, checking logs, and creating or editing pull requests.
- [DATA_EXFILTRATION]: Transmits repository metadata and user-approved content to GitHub. This is the intended functionality and uses a well-known service.
- [PROMPT_INJECTION]: Recognizes an attack surface for indirect prompt injection because the skill ingests branch diffs and commit logs that could contain malicious instructions. The risk is mitigated by a mandatory manual review step where the user must confirm the generated PR title and body before submission.
- Ingestion points: git diff and git log output (SKILL.md)
- Boundary markers: Not present
- Capability inventory: gh pr create, gh pr edit (SKILL.md)
- Sanitization: None identified for the ingested git data
Audit Metadata