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