prompt-engineering

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes numerous examples using the belt CLI tool (via belt app run) to interact with AI models. These are standard usage examples for the inference.sh platform and are executed in the context of prompting techniques.
  • [REMOTE_CODE_EXECUTION]: The skill mentions installation of the belt CLI using npx skills add, which is the standard mechanism for adding skills on this platform. The installation instructions reference a GitHub repository (inference-sh/skills) belonging to the platform's official organization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:18 PM
Security Audit — agent-trust-hub — prompt-engineering