extract

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes local project files to identify patterns, creating an indirect prompt injection surface where malicious content in source files could influence agent behavior.
  • Ingestion points: Local source files searched for design system keywords (SKILL.md).
  • Boundary markers: No delimiters or instructions to ignore embedded content are specified.
  • Capability inventory: File system reading, writing, and deletion associated with migration and documentation.
  • Sanitization: No content validation is performed.
  • [SAFE]: The instructions are legitimate and follow software engineering best practices for design system maintenance.
  • [NO_CODE]: No executable scripts or binary files are provided within the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 04:49 AM