video-look-sound
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill contains no executable code, scripts, or remote dependencies. It consists entirely of organizational instructions for a video production workflow.
- [INDIRECT_PROMPT_INJECTION]: The workflow involves processing user-provided scripts and character references. While this represents a data ingestion surface, the skill provides a structured framework for documenting production decisions, which helps maintain consistency and clarity. Evidence of ingestion: 'after the script and recurring-character references are settled'. Boundary markers: None explicitly mentioned in the instructions. Capability inventory: Use of
ffprobefor audio measurement, and implied tools for narration and video generation. Sanitization: Not explicitly addressed, but the structured document sections serve as a form of validation.
Audit Metadata