image-to-video

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as an instructional manual for the infsh CLI tool. It outlines how to use various AI models (like Wan 2.5 i2v and Seedance) for image-to-video generation.
  • [SAFE]: All external references point to the official domain (inference.sh) and its associated GitHub repository (inference-sh/skills) for documentation and installation instructions. These are legitimate resources for the tool described.
  • [SAFE]: The skill employs platform-level security by using the allowed-tools frontmatter field to restrict the agent's command-line access exclusively to the infsh utility.
  • [SAFE]: No malicious patterns such as prompt injection, data exfiltration, obfuscation, or unauthorized privilege escalation were identified. The instructions and code examples follow standard best practices for the intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 11:26 PM