refactor
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from repository files during its refactoring workflow. Ingestion points: Files are read via the Read tool in Phase 0 and Phase 2 (SKILL.md). Boundary markers: No specific delimiters or instructions are used to distinguish file content from the agent's instructions. Capability inventory: The skill possesses Edit, Write, and Bash tools and can call external skills like /simplify to modify the file system. Sanitization: The skill does not validate or escape the content of the files it refactors.
- [DYNAMIC_EXECUTION]: The skill executes a JavaScript file using a path constructed from the CLAUDE_PLUGIN_ROOT environment variable (SKILL.md).
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git log and wc commands for calculating file metrics during target detection (references/target-detection.md) and node to run a status script.
Audit Metadata