clean-code
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted source code provided by the user.
- Ingestion points: Target source code files or directories specified by the user during the workflow (Workflow Step 1).
- Boundary markers: The skill specifies a rigid reporting format (Workflow Step 4) and instructs the agent to ignore content elided with placeholders like '// ...'.
- Capability inventory: The skill is restricted to analyzing code and generating text reports or code refactoring suggestions. It does not utilize shell execution, network access, or file-writing tools.
- Sanitization: No explicit sanitization of input code is defined; however, the agent's output is intended for manual user review and the skill explicitly states it 'never modifies code' automatically.
- [NO_CODE]: The skill consists entirely of Markdown instruction and reference files. It does not include any scripts (Python, JavaScript, shell) or compiled binaries.
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, obfuscation, or persistence mechanisms were detected. The skill's behavior is consistent with its stated purpose of providing code cleanliness analysis based on established software engineering principles.
Audit Metadata