explainer-video-guide

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions and CLI tools hosted on the vendor's official GitHub repository (inference-sh) and uses package identifiers (belt-sh/cli) belonging to the vendor namespace. These are standard resources for the intended functionality.
  • [COMMAND_EXECUTION]: The skill uses Bash to run the belt CLI. The execution environment is restricted to this specific tool via the allowed-tools field in the frontmatter, preventing arbitrary command execution.
  • [SAFE]: The skill follows security best practices, such as requiring explicit login (belt login) for sensitive operations and providing clear documentation for its pipeline. No obfuscation, persistence mechanisms, or unauthorized data access patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 04:34 AM
Security Audit — agent-trust-hub — explainer-video-guide