Granola Meeting Notes

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script granola.js included in the plugin root to list and display meeting data.
  • [DATA_EXFILTRATION]: The skill accesses sensitive personal data by reading meeting notes and transcripts from the Granola app's local macOS cache.
  • [PROMPT_INJECTION]: The skill processes untrusted data from meeting transcripts, which can lead to indirect prompt injection.
  • Ingestion points: Data enters the context via list, show, search, and export commands in SKILL.md.
  • Boundary markers: None provided in the instructions.
  • Capability inventory: Execution of subprocesses via the granola.js tool.
  • Sanitization: No evidence of data sanitization before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 09:53 PM
Security Audit — agent-trust-hub — Granola Meeting Notes