videodb
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill enforces secure credential management by instructing the agent to rely on environment variables or .env files, explicitly warning against direct handling or storage of API keys by the AI.
- [SAFE]: The provided WebSocket listener script (scripts/ws_listener.py) implements robust local state management, ensuring that session artifacts and events are stored in a private directory with restricted (0o700) permissions.
- [SAFE]: All network operations are transparently aligned with the skill's core purpose, targeting official VideoDB API endpoints and user-supplied media URLs for ingestion and processing.
- [SAFE]: Subprocess calls are limited to the execution of Python code using the official SDK through clearly defined templates, with no evidence of obfuscation or execution of unverifiable remote scripts.
Audit Metadata