wan-t2v-video
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the analyzed skill.
- [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters, override agent behavior, or extract system prompts. The inclusion of model names and prompt templates is consistent with the skill's stated purpose for video generation.
- [EXTERNAL_DOWNLOADS]: The skill does not contain any commands to download external scripts, binary executables, or third-party packages. References to model files (.safetensors) are standard for AI workflows and do not involve remote code execution.
- [DATA_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or unauthorized network operations were detected. The skill operates within the context of a video generation environment.
- [COMMAND_EXECUTION]: The skill provides JSON-formatted workflow data intended for use with AI processing nodes (such as ComfyUI). It does not contain shell commands, system calls, or scripts that execute arbitrary code on the host system.
Audit Metadata