normalize
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus on standard UI refactoring and design consistency tasks without any detected malicious patterns.
- [DATA_EXPOSURE]: The skill instructs the agent to search local project files (e.g., using
grep) to discover design documentation. This file access is limited to the local environment and is necessary for the skill's stated purpose. - [COMMAND_EXECUTION]: The skill suggests running routine development commands such as linting, type-checking, and testing. These operations are expected within a frontend development workflow.
- [PROMPT_INJECTION]: The skill uses persona-based language ("You are a brilliant frontend designer") to guide the agent's behavior for the task, but does not attempt to bypass safety filters or override system constraints.
Audit Metadata