prompt-engineering
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill provides educational content and examples for prompt engineering across various AI modalities.
- [COMMAND_EXECUTION]: Demonstrates the use of the
infshCLI tool for legitimate tasks such as authentication and executing model inferences. - [EXTERNAL_DOWNLOADS]: References additional skills for installation from the vendor's official 'inference-sh/skills' repository via the
skillsutility. - [DATA_EXFILTRATION]: Network connections are made exclusively to official vendor domains including inference.sh and cloud.inference.sh.
Audit Metadata