code-like-michael
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides stylistic and structural guidelines for software development. It contains no executable scripts, remote resource requests, or commands that interact with the host system or network. All analyzed files are markdown documents providing instructional content.
- [PROMPT_INJECTION]: As the skill is designed to review and refactor code, it has an indirect prompt injection surface where the agent processes untrusted code. No specific evidence of malicious instructions was found in the skill itself. The instructions encourage the use of boundary markers and validation, which can mitigate injection risks in processed data.
Audit Metadata