tavus-replica-video

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides comprehensive instructions for interacting with official Tavus API endpoints. It correctly identifies the need for secure credential management, advising that API keys be treated as secrets.
  • [SAFE]: The documentation includes a dedicated section on consent and rights, establishing strict requirements for the ethical use of training data and likeness. This proactive approach mitigates risks related to unauthorized content generation.
  • [SAFE]: All external URLs are directed toward official service documentation or use standard placeholders for cloud storage. No suspicious remote code execution or unauthorized download patterns were detected.
  • [SAFE]: The instructions for script writing and PAL (Persona) configuration include boundary-setting advice (e.g., avoiding bracketed directions) that helps prevent unintended model behavior when processing user-supplied text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 01:51 PM
Security Audit — agent-trust-hub — tavus-replica-video