heygen-creative
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
pythonandffmpegto process video and audio assets based on local script files. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied narration scripts (e.g.,
creative/heygen/scripts/EXP-XXX-founder.md) which are used as input for the video generation process. - Ingestion points: Reads narration scripts from the local file system.
- Boundary markers: No specific boundary markers or instructions are provided to the agent to treat script content as data rather than instructions.
- Capability inventory: The skill possesses the capability to execute Python scripts (
creative/heygen/run.py) and media tools (ffmpeg). - Sanitization: The instructions do not specify any sanitization or validation of the input script content before it is passed to the generation tools.
Audit Metadata