ai-video-gen
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided text prompts and image URLs for video generation. These inputs are interpolated into API requests sent to external providers.
- Ingestion points: User input flows through the
prompt,reference_image_url, andtail_image_urlfields defined in the workflow templates inSKILL.md. - Boundary markers: No specific delimiters are used in the prompt templates to separate user instructions from system context.
- Capability inventory: The skill facilitates network operations (HTTP POST/GET) to external API endpoints.
- Sanitization: No explicit sanitization or filtering of user input is implemented within the skill templates.
- [EXTERNAL_DOWNLOADS]: The skill documentation describes network interactions with legitimate video generation platforms including HeyGen (
api.heygen.com), fal.ai, and Google Gemini APIs.
Audit Metadata