extract
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues or malicious patterns were detected in the skill's instructions or logic. The tool performs standard codebase analysis and refactoring tasks within the user's project environment.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted codebase data and has file-write capabilities. This is documented as a risk factor inherent to its refactoring function. Ingestion points: Source code files and UI components analyzed during the discovery phase. Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded instructions in the code being analyzed. Capability inventory: The skill can read files using tools like
grep, create new component files, and delete code during the migration phase. Sanitization: No specific sanitization or validation of the code content is described before it is processed or extracted.
Audit Metadata