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

faceswap

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill communicates with api.heygen.com, which is the official API endpoint for the HeyGen AI video platform. This is a well-known service and the interaction is necessary for the skill's primary function of face swapping.
  • [CREDENTIALS_SAFE]: The skill correctly instructs users to manage their API keys via the HEYGEN_API_KEY environment variable, avoiding hardcoded secrets and following standard security best practices for secret management.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of source_image_url and target_video_url. While these URLs are processed by an external API, the skill documentation defines a narrow schema for these inputs, and the underlying platform handles the network execution to a specific, legitimate service domain.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:09 AM
Security Audit — agent-trust-hub — faceswap