clean-code
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and process arbitrary codebases provided by users, which may contain malicious instructions embedded in comments or data.
- Ingestion points: Any codebase targeted for refactoring (referenced in SKILL.md and README.md).
- Boundary markers: The skill instructions lack explicit boundary markers or warnings to the agent to disregard instructions found within the processed code.
- Capability inventory: The skill workflow requires the agent to read and write files, as well as execute test suites to verify behavior preservation.
- Sanitization: There is no evidence of sanitization or filtering of the external code before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill instructs the agent to run build and test commands (tests, lint, type-check, build) on the codebase being refactored as part of the refactoring loop. This is consistent with the skill's primary purpose.
- [EXTERNAL_DOWNLOADS]: The landing page (index.html) references assets from trusted organizations and well-known services, such as fonts from Google and the skill's source code on GitHub.
Audit Metadata