extract
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No security issues detected. The skill's instructions focus on code analysis and refactoring within a local design system context.
- [COMMAND_EXECUTION] (SAFE): The skill describes searching the local filesystem (e.g., 'grep for "design system"') and modifying files. These are expected actions for a code-manipulation skill and do not involve suspicious shell commands or privilege escalation.
- [PROMPT_INJECTION] (SAFE): Although the prompt uses terms like 'CRITICAL' and 'IMPORTANT', these are contextually appropriate instructions for the AI's task (e.g., advising the AI to ask before creating a new directory structure) rather than attempts to bypass LLM safety filters or ignore system instructions.
- [DATA_EXFILTRATION] (SAFE): No network operations, API calls, or external data transfer mechanisms were found in the skill definition.
Audit Metadata