create-video
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts to generate video content, creating a potential surface for indirect prompt injection where instructions embedded in the input could influence agent behavior.
- Ingestion points: User-provided text prompts used for video generation as described in
SKILL.mdandreferences/video-agent.md. - Boundary markers: Absent. The skill instructions do not specify delimiters or 'ignore embedded instructions' warnings for user-supplied data.
- Capability inventory: The skill possesses network capabilities to interact with HeyGen's API and upload endpoints (
api.heygen.com,upload.heygen.com) for video creation and asset management (SKILL.md,references/video-agent.md,references/assets.md,references/video-status.md). - Sanitization: Absent. No sanitization, escaping, or filtering of the user-provided prompt is defined before it is processed by the agent.
Audit Metadata