heygen
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted natural language prompts to generate AI videos, which presents a surface for indirect prompt injection.
- Ingestion points: User-supplied prompts are processed by the
mcp__heygen__generate_video_agenttool and the/v1/video_agent/generateendpoint, as detailed inSKILL.mdandreferences/video-agent.md. - Boundary markers: There are no documented boundary markers or system instructions to delimit user input or prevent the execution of embedded instructions within the prompt.
- Capability inventory: The skill possesses capabilities to generate, list, and delete videos, as well as upload and manage media assets via the HeyGen API.
- Sanitization: The provided documentation and code examples do not include mechanisms for sanitizing or validating the content of the prompts before they are sent to the API.
Audit Metadata