switchyard-docs

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references standard GitHub Actions from well-known providers such as astral-sh/setup-uv and peaceiris/actions-gh-pages within the documentation for the CI workflow. These are widely used in the development community.
  • [COMMAND_EXECUTION]: The skill includes a reference table for standard documentation tasks using make and uv commands (e.g., make live, make publish). These are intended for local development and build processes.
  • [CREDENTIALS_UNSAFE]: The documentation guidelines mention environment variables like NVIDIA_API_KEY and OPENROUTER_API_KEY as placeholders and configuration fallbacks for user-written examples. No hardcoded secrets are present.
  • [PROMPT_INJECTION]: The instructions do not contain patterns aimed at overriding agent safety guidelines or system prompts. The use of 'IMPORTANT' and 'CRITICAL' in the text refers to documentation standards and CI integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 07:48 AM
Security Audit — agent-trust-hub — switchyard-docs