things3-manager

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses osascript to open things:/// URLs for creating and updating tasks. It uses subprocess.run with a list of arguments and properly URL-encodes all user input using urllib.parse.quote, which effectively prevents command injection.
  • [EXTERNAL_DOWNLOADS]: The setup.sh script installs the things-py library from the Python Package Index (PyPI). This is a well-known library used for its intended purpose of reading the local Things 3 SQLite database.
  • [SAFE]: The skill stores its configuration and environment data in a localized .skills-data directory within the project root, adhering to recommended data isolation practices. No patterns of data exfiltration, obfuscation, or persistence were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:15 AM
Security Audit — agent-trust-hub — things3-manager