skills/guyronnen/openmontage/heygen/Gen Agent Trust Hub

heygen

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text prompts to generate video content via the HeyGen API, which represents a standard surface for indirect prompt injection where malicious instructions could be included in the video script.
  • Ingestion points: User input prompts are processed in references/video-agent.md and references/video-generation.md.
  • Boundary markers: None identified; user input is passed directly to the external API for processing.
  • Capability inventory: The skill uses mcp__heygen__* tools and direct network API calls to HeyGen (api.heygen.com) for video generation.
  • Sanitization: Relies on the service provider's safety guardrails without local filtering.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of video assets, thumbnails, and preview clips from HeyGen's official infrastructure including api.heygen.com, upload.heygen.com, and *.heygen.ai. These downloads are necessary for the skill's core functionality and target official service domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:09 AM
Security Audit — agent-trust-hub — heygen