video-ad-specs

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the belt CLI tool from the belt-sh organization using npx and points to installation guides hosted on the inference-sh GitHub repository. These downloads are necessary for the skill's documented functionality.
  • [COMMAND_EXECUTION]: The skill provides numerous examples of using the belt CLI to interface with remote AI models for video generation, text-to-speech conversion, and video editing tasks. These commands are integral to the skill's purpose as an automation guide for ad production.
  • [SAFE]: No indicators of credential theft, data exfiltration, or malicious prompt injection were detected. The skill's operations are transparent and consistent with its stated goal of helping users create platform-specific video advertisements.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:13 PM
Security Audit — agent-trust-hub — video-ad-specs