stitch-extract-design-md

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill incorporates explicit anti-patterns that instruct the AI agent to avoid reading, printing, or storing sensitive information such as API keys, secrets, or cookies.
  • [EXTERNAL_DOWNLOADS]: The skill mentions documentation and support material from a repository on GitHub associated with Google. This is a well-known organization and service.
  • [COMMAND_EXECUTION]: References a local helper script (scripts/export-gemini-skill.py) used for maintenance and portability. This is a standard development practice for skill management.
  • [PROMPT_INJECTION]: The skill processes project source code (e.g., CSS, JS, framework configs) which constitutes an indirect prompt injection surface.
  • Ingestion points: Reads frontend source code, stylesheets, and local configuration files during the extraction process (SKILL.md).
  • Boundary markers: No specific boundary markers or delimiters are defined to isolate the untrusted code content from the agent's instructions.
  • Capability inventory: The skill's capabilities are restricted to local file reading and calling design-system management tools (SKILL.md).
  • Sanitization: No specific sanitization or filtering logic is described for the ingested source data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 06:07 PM
Security Audit — agent-trust-hub — stitch-extract-design-md