cleanse
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and modifies user-provided code, which acts as an ingestion point for potentially malicious instructions embedded in comments or strings.
- Ingestion points: Target files and directories provided by the user for refactoring review.
- Boundary markers: The instructions do not define delimiters or specific safety markers to differentiate code from embedded instructions.
- Capability inventory: The skill makes direct edits to files and is instructed to run local project lint or build commands.
- Sanitization: No filtering or sanitization of the ingested code content is performed.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute project-specific lint or build commands to verify refactoring changes, which involves running local binaries.
Audit Metadata