distill
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and modify external codebases. \n
- Ingestion points: Instructions in
SKILL.mddirect the agent to analyze the current 'codebase' and 'designs' provided via theTARGETargument. \n - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed codebase are provided. \n
- Capability inventory: The 'Code Simplification' section of
SKILL.mdexplicitly instructs the agent to 'Remove unused code', 'Flatten component trees', and 'Consolidate styles', requiring file-read and file-write capabilities. \n - Sanitization: The skill lacks explicit sanitization or validation logic for the content it reads from the codebase before processing or re-writing it.
Audit Metadata