stitch-design-taste

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of Markdown instructions and YAML configuration for defining design standards. No executable scripts, binaries, or automated shell commands were found.
  • [SAFE]: External URLs referenced, such as Google's Stitch labs and the Picsum placeholder service, are well-known and consistent with the skill's purpose of design and prototyping.
  • [SAFE]: No patterns of data exfiltration, credential theft, or unauthorized file access were detected. The skill does not access sensitive system paths or environment variables.
  • [SAFE]: The instructional language uses authoritative design constraints (e.g., banning certain fonts or layouts), which is appropriate for a style-enforcement skill and does not represent a malicious attempt to override agent safety protocols.
  • [SAFE]: The configuration in agents/openai.yaml proactively disables implicit invocation, which is a security best practice that prevents the skill from being triggered without explicit user intent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 09:16 PM