gh-fix-ci
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill executes the GitHub CLI (
gh) and a local script (inspect_pr_checks.py). While necessary for the skill's function, executing local code requires user trust in the script's contents. - [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8). 1. Ingestion points: GitHub Actions logs are ingested via
gh run view --log. 2. Boundary markers: No explicit delimiters or instructions are used to distinguish log content from agent instructions. 3. Capability inventory: The agent has the capacity to modify the repository and execute local tests. 4. Sanitization: No sanitization is performed on the ingested logs before they are used to generate plans. - [NO_CODE] (LOW): The bundled script
scripts/inspect_pr_checks.pymentioned in the documentation is missing from the provided files, preventing a thorough security review of its execution logic.
Audit Metadata