Skills
Navigate
skills/thecoldblooded/openmontage/ai-video-gen/Gen Agent Trust Hub

ai-video-gen

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with official HeyGen API endpoints (api.heygen.com and resource.heygen.ai) to generate and retrieve video content. These are recognized services for AI media production.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text prompts to generate video content. While this creates a surface for indirect prompt injection, it is the primary function of the skill and is handled through standard API parameters.
  • Ingestion points: input.prompt field in the GenerateVideoNode workflow (SKILL.md).
  • Boundary markers: Not present.
  • Capability inventory: Network POST requests via requests (Python) and fetch (TypeScript) to the HeyGen API.
  • Sanitization: None specified for the prompt text.
  • [CREDENTIALS_UNSAFE]: The skill requires HEYGEN_API_KEY for authentication. The instructions correctly direct the user to store this in an environment variable rather than hardcoding it, following security best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:50 PM