happyhorse

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides links to documentation and installation instructions from inference.sh and GitHub repositories under the inference-sh organization. These are treated as well-known service references for the functionality provided and do not involve untrusted remote code execution.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool (associated with the inference.sh platform) to run video generation models. These commands (belt login, belt app run) are legitimate use cases for the skill's stated purpose of interfacing with the AI models.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 10:10 AM
Security Audit — agent-trust-hub — happyhorse