stitch-taste-design

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional text and design templates. It does not contain executable code, request elevated permissions, or attempt to persist across sessions.
  • [EXTERNAL_DOWNLOADS]: The skill references a repository under Google Labs as its source. This is a reference to a well-known and trusted organization and does not involve automated remote code execution.
  • [PROMPT_INJECTION]: The skill incorporates a step to audit project screens using the Stitch MCP tool. This ingestion point for external project data is standard for the skill's purpose as a design auditor and does not include instructions to bypass safety filters or execute content from the audited screens. Ingestion point: project screens via Stitch MCP (SKILL.md); Boundary markers: absent; Capability inventory: markdown generation; Sanitization: absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 03:01 PM
Security Audit — agent-trust-hub — stitch-taste-design