skills/infsh-skills/skills/happyhorse/Gen Agent Trust Hub

happyhorse

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill facilitates video generation and editing using Alibaba's HappyHorse models through the 'belt' CLI tool provided by inference.sh.
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions for the 'belt' CLI from the vendor's GitHub repository (github.com/inference-sh). These are documented neutrally as legitimate vendor resources.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted user data.
  • Ingestion points: 'prompt', 'first_frame', 'reference_images', and 'video' parameters in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: Execution of the 'belt' CLI via the Bash tool.
  • Sanitization: None present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 01:48 PM