scenario-minimax-video
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of natural language instructions for using platform-specific tools (
search,model_run,upload_asset, etc.) to generate video content. All instructions are consistent with the stated purpose of video generation and asset management. - [INDIRECT_PROMPT_INJECTION]: The skill describes processes that involve reading external data, such as model schemas and job statuses. This creates a surface for indirect prompt injection if external systems were compromised, but the skill itself implements standard tool-use patterns for its intended functionality.
Audit Metadata