skills/shinpr/nautilus/recipe-vision/Gen Agent Trust Hub

recipe-vision

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill exclusively manages product documentation and strategy files within the docs/product/ directory. No sensitive system paths, credentials, or configuration files are accessed.- [SAFE]: A 'user-in-the-loop' protocol is enforced, with a mandatory blocking confirmation step ([STOP — BLOCKING]) that prevents the agent from performing write operations until the user explicitly approves the generated content.- [SAFE]: No external network requests, remote code downloads, or dynamic execution patterns were identified in the instructions or templates.- [SAFE]: Data ingestion is limited to local project documentation files, and the output is restricted to relevant product-specific markdown files.- [NO_CODE]: The skill consists entirely of instructional markdown and templates without any associated scripts or executable code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 10:15 PM
Security Audit — agent-trust-hub — recipe-vision