extract
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill involves analyzing external file content within a user-defined target area. This introduces a surface for indirect prompt injection, where malicious content in those files could attempt to subvert the agent's instructions.
- Ingestion points: Content of files within the target parameter or identified via search (SKILL.md).
- Boundary markers: The instructions do not include specific delimiters or warnings to ignore instructions found within the processed files.
- Capability inventory: The skill focuses on code analysis, searching, and writing/refactoring. It does not include network operations or execution of untrusted code.
- Sanitization: No sanitization or validation of the ingested file content is mentioned.
- [COMMAND_EXECUTION]: The skill suggests using the grep utility to search the local filesystem for design patterns, components, and design tokens.
Audit Metadata