llm-models

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires permission to execute commands using the infsh (inference-sh) CLI tool via the Bash(infsh *) allowance. This tool is the vendor's primary interface for running LLM applications.
  • [EXTERNAL_DOWNLOADS]: The documentation provides instructions to install additional skills from the vendor's own repository using npx skills add inference-sh/skills@.... These are recognized vendor resources and do not represent a security risk.
  • [SAFE]: All external URLs and resources point to official vendor domains (inference.sh, cloud.inference.sh). There are no signs of credential exposure, obfuscation, or unauthorized data access.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 08:24 PM