ci-fixer
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill uses well-known services and follows standard practices for CI failure resolution. A potential ingestion surface for indirect prompt injection was reviewed and determined to be a routine part of the development workflow.
- [PROMPT_INJECTION]: The skill processes data from CI logs and PR status updates, creating a theoretical surface for indirect prompt injection. Ingestion points: Data is fetched via 'gh pr checks' and 'gh run view --log-failed'. Boundary markers: The instructions do not define specific delimiters for log content. Capability inventory: The skill can modify local source code, run tools via 'npx', and push commits. Sanitization: No explicit sanitization of log output is performed. This behavior is standard for tools interacting with development infrastructure.
Audit Metadata