prompt-engineering

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as an educational resource for prompt engineering. It demonstrates how to use the belt CLI tool for different AI tasks including text, image, and video generation.
  • [COMMAND_EXECUTION]: The skill contains numerous examples of belt app run commands. These are documented examples for interacting with the inference.sh platform and do not perform unauthorized or dangerous operations.
  • [EXTERNAL_DOWNLOADS]: The skill references installation scripts and documentation from official and well-known repositories (e.g., github.com/inference-sh, cloud.inference.sh). These references are neutral and used for standard setup procedures.
  • [SAFE]: Instructions for belt login are standard for CLI tools and follow best practices by not hardcoding credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:39 PM
Security Audit — agent-trust-hub — prompt-engineering