ai-video-gen
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of user-controlled data (text prompts and image URLs) which are then passed to the HeyGen API for video generation. This represents an attack surface for indirect prompt injection where malicious content in the input could affect the behavior of the external service.
- Ingestion points: SKILL.md (via the prompt, reference_image_url, and tail_image_url input fields).
- Boundary markers: No delimiters or instructions to ignore embedded commands are present in the provided examples; user inputs are directly interpolated into the API payload.
- Capability inventory: The skill uses tools to perform network POST requests to https://api.heygen.com/v1/workflows/executions.
- Sanitization: There is no evidence of input validation or sanitization before the data is transmitted to the external gateway.
- [EXTERNAL_DOWNLOADS]: The skill documentation includes code examples that utilize the requests library and fetch API to communicate with api.heygen.com. These network operations are core to the skill's primary functionality and target a well-known service provider.
Audit Metadata