clean-coder
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external code provided by users or other agents for the purpose of refactoring and review. This creates a surface where malicious instructions could be embedded within code comments or string literals.
- Ingestion points: The agent is instructed to scan and review code snippets in the 'Steps' section of
SKILL.md. - Boundary markers: The instructions do not define clear delimiters or specialized tokens to separate user-provided code from the agent's instructions.
- Capability inventory: While the skill itself defines no tools, the agent's output (refactored code) is intended to be incorporated into software projects, potentially affecting downstream code quality or security if the agent is manipulated.
- Sanitization: There are no instructions for the agent to sanitize or escape input before processing, although the 'Security & Guardrails' section explicitly warns the agent against removing security-critical logic during refactoring.
- [NO_CODE]: The skill consists entirely of Markdown instructions and YAML metadata. It does not include any Python scripts, Node.js packages, or shell commands.
Audit Metadata