codebase-cleanup-refactor-clean
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The playbook references official GitHub Actions and well-known quality tools.
- References official repositories including actions/checkout and github/codeql-action.
- Includes examples for integration with well-known services like CodeRabbit and CodiumAI.
- [PROMPT_INJECTION]: The skill is designed to process untrusted user-provided source code for refactoring.
- Ingestion points: Source code provided via prompts (mapped to $ARGUMENTS) or referenced files in the implementation-playbook.md and SKILL.md context.
- Boundary markers: Absent; no specific delimiters are instructed for isolating untrusted user input.
- Capability inventory: Instructions are limited to code analysis, refactoring, and documentation; no tool execution or file-system write capabilities are requested in the frontmatter configuration.
- Sanitization: Absent; the skill does not explicitly provide instructions for escaping or validating user input code.
Audit Metadata