codebase-cleanup-refactor-clean
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, user-provided code for refactoring analysis and implementation, creating a surface for indirect prompt injection.
- Ingestion points: The skill instructions explicitly state to "Analyze and refactor the provided code."
- Boundary markers: There are no instructions defining delimiters or boundary markers to separate code content from instructions for the agent.
- Capability inventory: The skill is designed to have the agent "Apply changes" and "Validate with tests," which involves file-system writes and potentially command execution if the agent has those capabilities enabled.
- Sanitization: The skill lacks instructions for sanitizing or escaping the content of the provided code before processing.
Audit Metadata