twelvelabs-video-understanding

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows security best practices by providing explicit warnings regarding the processing of biometric data (faces and voices) and emphasizing the need for user consent and legal compliance.
  • [SAFE]: Instructions for interacting with external services correctly point to official vendor domains (twelvelabs.io) and repositories (github.com/twelvelabs-io), adhering to the trusted vendor policy for the associated TwelveLabs platform.
  • [SAFE]: The skill includes robust guidance for mitigating potential output inaccuracies through the use of low temperature settings, structured JSON schemas, and anchoring model claims to specific video evidence.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 01:52 PM
Security Audit — agent-trust-hub — twelvelabs-video-understanding