llm-models
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill includes an installation one-liner that fetches a script from the vendor's official domain (https://cli.inference.sh) and executes it via the shell. This is the documented installation procedure for the vendor's CLI.
- [EXTERNAL_DOWNLOADS]: The installation script downloads architecture-specific binaries from the vendor's distribution server (dist.inference.sh) and verifies their integrity via checksums.
- [COMMAND_EXECUTION]: The skill is configured to execute the infsh CLI tool for authenticating, listing models, and performing inference tasks.
Audit Metadata