evernote-connector

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the evernote3 library, which is a standard community fork of the official Evernote SDK for Python 3.
  • [COMMAND_EXECUTION]: The agent executes the scripts/evernote.py script to perform operations on the user's Evernote account.
  • [DATA_EXFILTRATION]: The CLI tool communicates with Evernote's official API endpoints to synchronize user content.
  • [CREDENTIALS_UNSAFE]: Developer tokens and OAuth access tokens are handled correctly using the EVERNOTE_TOKEN environment variable.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill reads note content from an external source. * Ingestion points: Evernote note content read via scripts/evernote.py. * Boundary markers: Not used in the script's output to the agent. * Capability inventory: The agent can create, list, update, and delete notes and notebooks. * Sanitization: The script strips XML/HTML tags using the enml_to_text function before the agent processes the content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 11:27 AM
Security Audit — agent-trust-hub — evernote-connector