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

happyhorse

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation scripts from 'inference.sh' and 'github.com/inference-sh'. These are official resources related to the video generation service integrated by the skill.
  • [COMMAND_EXECUTION]: The skill utilizes the 'belt' CLI tool to run video generation apps. Command execution is constrained to the 'belt' tool as defined in the 'allowed-tools' frontmatter configuration.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface typical of media generation tools.
  • Ingestion points: User-provided text prompts and external image/video URLs are accepted through the '--input' JSON parameter in 'SKILL.md'.
  • Boundary markers: No specific delimiters are used to isolate user-supplied prompts within the command templates.
  • Capability inventory: The skill uses the 'belt' CLI tool, which interfaces with a remote API to process video tasks.
  • Sanitization: User inputs are placed directly into JSON objects for the CLI tool, relying on the underlying platform's handling of structured data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 07:03 PM
Security Audit — agent-trust-hub — happyhorse