video-ad-specs

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill provides legitimate educational content and tool integration for video ad production.
  • [EXTERNAL_DOWNLOADS]: The skill references external resources for installation and configuration guidelines.
  • Fetches setup instructions from a public GitHub repository: https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
  • [COMMAND_EXECUTION]: The skill provides examples for using the belt CLI to manage video generation workflows.
  • Commands include belt login, belt app run, and installation via npx.
  • [REMOTE_CODE_EXECUTION]: The skill utilizes the belt tool to trigger remote application execution on the inference.sh platform.
  • Examples demonstrate invoking various AI models (e.g., bytedance/seedance-2-0, google/veo-3-1-fast) to generate video and audio assets based on user-provided prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 03:53 PM
Security Audit — agent-trust-hub — video-ad-specs