gh-fix-ci
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill uses
subprocess.runto interact withgitand the GitHub CLI (gh). This is a necessary component of its functionality to inspect repository state and retrieve logs. The implementation follows security best practices by passing command arguments as lists rather than using a shell environment, which helps prevent command injection.\n- Indirect Prompt Injection Surface: The skill ingests untrusted data in the form of GitHub Action logs to identify failure points.\n - Ingestion points: Logs are retrieved via
gh run view --logand the GitHub API inscripts/inspect_pr_checks.py.\n - Boundary markers: The output does not currently use specific delimiters or instructions to treat log content as data only.\n
- Capability inventory: The skill allows for local command execution and file writing to implement proposed fixes.\n
- Sanitization: Log content is processed for snippets without explicit sanitization. This is a common characteristic of log-analysis tools and is considered a low-severity surface for the skill's primary purpose.
Audit Metadata