prompt-engineering
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions for the infsh CLI hosted on GitHub (inference-sh/skills) and provides commands to install related skills via npx. These resources originate from the platform's official repositories.
- [COMMAND_EXECUTION]: Includes examples using the infsh CLI tool to run AI model inferences. These commands are the primary function of the skill and are restricted to the infsh namespace as defined in the skill's allowed-tools configuration.
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The skill's behavior strictly matches its stated goal of providing prompt engineering guidance.
Audit Metadata