building-design

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill mentions using npx @google/design.md for optional linting of design files. This command fetches and executes a package from a well-known organization's official registry for its intended purpose.\n- [SAFE]: The workflow processes user-supplied requirements and specifications to generate markdown documentation. The instructions provide explicit boundary markers and guidelines for handling content gaps to ensure the agent does not autonomously invent or execute unintended instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 09:01 AM
Security Audit — agent-trust-hub — building-design