extract
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze untrusted code within a target area to discover reusable patterns, which allows content in those files to influence the agent's context.
- [INDIRECT_PROMPT_INJECTION]: Ingestion points: Files located in the user-specified target directory (SKILL.md). Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the processed files. Capability inventory: The skill performs file reading (searching for patterns), file writing (creating new components/tokens), and file deletion (removing dead code). Sanitization: No sanitization or validation of the extracted code content is performed before processing.
Audit Metadata