heygen-creative

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (run.py) and standard media processing binaries (ffmpeg, ffprobe) to slice audio and stitch video outputs.
  • [CREDENTIALS_UNSAFE]: The documentation instructs users to store sensitive API credentials, such as HEYGEN_API_KEY, in environment variables, which is a secure and recommended practice.
  • [PROMPT_INJECTION]: The skill ingests narration scripts from local markdown files, which represents an indirect prompt injection surface.
  • Ingestion points: Files located in creative/heygen/scripts/*.md.
  • Boundary markers: None identified in the documentation.
  • Capability inventory: Local command execution (Python, ffmpeg) and network requests to external APIs (HeyGen, OpenAI).
  • Sanitization: No explicit sanitization or content validation is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 10:43 AM
Security Audit — agent-trust-hub — heygen-creative