happyhorse

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions for a command-line tool (belt) from a GitHub repository (raw.githubusercontent.com/inference-sh/skills/). This is a common pattern for platform-specific tooling and follows the [TRUST-SCOPE-RULE] for well-known services.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI to run video generation applications (e.g., belt app run alibaba/happyhorse-1-0-t2v). These commands are standard for the tool's documented purpose and do not involve privilege escalation or unauthorized access.
  • [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The skill's behavior matches its described purpose as a video generation utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:39 PM
Security Audit — agent-trust-hub — happyhorse