quality-review
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and associated scripts perform legitimate video processing, metadata analysis, and quality assurance tasks as described.
- [SAFE]: All provided Python scripts (e.g.,
timing.py,checklist.py,qc.py) rely exclusively on the Python standard library and operate on JSON data representing scene configurations or user-supplied briefs, without executing external code or making network requests. - [SAFE]: There are no detected patterns of prompt injection, data exfiltration, obfuscation, or persistence mechanisms. The skill operates within the expected agent environment.
- [SAFE]: The architecture uses sub-agents defined in reference files (e.g.,
agent-critic-roots.md,agent-qc-inspector.md) which include explicit constraints and safety boundaries, preventing them from overriding user decisions or performing unauthorized actions.
Audit Metadata