short-form-video
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a professional video production workflow using standard media tools like FFmpeg for intended technical purposes.
- [SAFE]: Command execution is limited to local project tasks and the Hyperframes framework's CLI, with no evidence of malicious injection or unauthorized access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external transcript data and audio files, creating an attack surface for indirect prompt injection. This is mitigated by the skill's primary purpose and a mandatory manual verification gate requiring the review of rendered frames. Ingestion points: transcript.json and audio/video assets. Boundary markers: None explicitly defined. Capability inventory: ffprobe, ffmpeg, and framework-specific CLI commands. Sanitization: Mandatory human-in-the-loop verification via Step 3 of the workflow.
Audit Metadata