code-refactoring-refactor-clean
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core purpose is to analyze and refactor code provided in the conversation context. This code represents untrusted input that could contain malicious instructions (e.g., in comments or strings). The skill lacks specific boundary markers or instructions to treat the input code strictly as data, which could lead the agent to inadvertently follow commands hidden within the source code.\n
- Ingestion points: User-provided source code via arguments or conversation history (SKILL.md).\n
- Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands.\n
- Capability inventory: The instructions direct the agent to 'Apply changes' and 'Update tests', which involves writing to the file system if the agent has the necessary tool access.\n
- Sanitization: Absent; no validation or filtering is performed on the input code content.
Audit Metadata