skills/glebis/claude-skills/granola/Gen Agent Trust Hub

granola

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses sensitive local files, specifically authentication tokens in ~/Library/Application Support/Granola/supabase.json and meeting metadata in cache-v4.json. This access is required for the skill's primary function of retrieving and exporting meeting content.- [DATA_EXFILTRATION]: Authentication tokens and meeting identifiers are transmitted to the official Granola API at api.granola.ai. This behavior is transparently documented and consistent with the vendor's service requirements.- [COMMAND_EXECUTION]: The skill utilizes Python scripts to query local data and manage exports. It also includes a shell script (sync.sh) used for automating the export process.- [PERSISTENCE]: The documentation includes instructions for creating a macOS LaunchAgent (com.user.granola-sync.plist) to run the synchronization script every 15 minutes. This is a standard and well-documented method for background automation on macOS.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 07:13 PM