explainer-video-guide
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a comprehensive guide for video production workflows using the
beltCLI tool. All provided code snippets are standard examples for using media generation APIs (e.g., Google Veo, ByteDance Seedance, and Fal.ai) via the vendor's infrastructure. - [EXTERNAL_DOWNLOADS]: The skill references the vendor's own documentation (
raw.githubusercontent.com/inference-sh/skills/) for installation instructions, which is a standard practice and within the trust scope of the vendor's resources. - [COMMAND_EXECUTION]: The shell commands included are purely illustrative examples of how to interact with a CLI tool (
belt) to generate media content. There are no attempts to execute arbitrary code, modify system files, or establish persistence. - [DATA_EXFILTRATION]: No patterns of sensitive data access or exfiltration were detected. All network operations are directed at the vendor's legitimate API endpoints for AI inference.
- [PROMPT_INJECTION]: The instructions do not contain any bypass attempts, role-play injections, or instructions to override agent safety guidelines.
Audit Metadata