faceswap
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns were detected. The skill interacts exclusively with official HeyGen API endpoints (api.heygen.com) and uses the HEYGEN_API_KEY environment variable for authentication, which is an industry-standard security practice.
- [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for the agent to process content from user-supplied URLs, creating a standard data ingestion surface.
- Ingestion points: The parameters
source_image_urlandtarget_video_urlin SKILL.md. - Boundary markers: Absent from the provided code and instructions.
- Capability inventory: Network requests (POST/GET) directed to api.heygen.com for workflow execution and status polling.
- Sanitization: Absent in the skill logic; safety validation is contextually delegated to the HeyGen API service provider.
Audit Metadata