vault-recipes

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is strictly scoped to recipe management within designated vault directories (03-Records/Clippings/Recipes/, 98-Spaces/, 99-Admin/). Operations are confined to these paths to maintain vault integrity.
  • [COMMAND_EXECUTION]: The instructions utilize the obsidian and notesmd-cli command-line interfaces for legitimate vault operations. These tools are used for their intended purposes, such as querying metadata, reading note sections, and searching for ingredients.
  • [EXTERNAL_DOWNLOADS]: The skill includes functionality to fetch recipe data from external URLs via the vault_clip_url tool. This is a core feature for expanding the collection, and the instructions specifically guide the agent to extract structured data into local templates, which acts as a controlled ingestion process.
  • [DATA_EXFILTRATION]: No unauthorized data transmission or sensitive file access was detected. Network usage is limited to authorized recipe fetching and communication with the designated 'Brain MCP' for remote vault access.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 07:59 AM
Security Audit — agent-trust-hub — vault-recipes