heygen
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional content and reference material for legitimate AI video production workflows. It emphasizes adherence to safety standards, such as verifying consent for digital twins and ensuring AI disclosure in accordance with regulations like the EU AI Act.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill references the HeyGen API endpoint and the requirement for an API key (
X-Api-Key) for integration purposes. However, it does not include any hardcoded credentials or instructions that would lead to the exfiltration of sensitive information. - [INDIRECT_PROMPT_INJECTION]: The skill involves processing user-provided briefs into video scripts. While this creates a surface for processing untrusted data, the skill is purely informational and does not implement high-risk capabilities such as arbitrary code execution or direct file system access, making the risk profile consistent with standard agent operations.
Audit Metadata