clean-code
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and refactor user-provided source code, creating an ingestion point for untrusted data that could contain hidden instructions.
- Ingestion points: Processes existing code for refactoring and quality review tasks as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or isolation techniques (such as XML tags or explicit "ignore" markers) to separate the agent's instructions from the code being processed.
- Capability inventory: The skill is scoped to code modification and structural refactoring; it does not explicitly define or invoke high-risk capabilities like network exfiltration, arbitrary command execution, or sensitive file system access.
- Sanitization: The skill does not provide mechanisms for sanitizing, escaping, or filtering embedded instructions that might be present in the target source code comments or strings.
Audit Metadata