skills/inf-sh/skills/llm-models/Gen Agent Trust Hub

llm-models

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill includes instructions to download and execute an installation script from the vendor's official domain (https://cli.inference.sh). This script is used to install the infsh command-line utility.
  • [EXTERNAL_DOWNLOADS]: The installation process fetches binary files and checksums from the vendor's distribution infrastructure (dist.inference.sh).
  • [COMMAND_EXECUTION]: The skill utilizes the infsh command to manage model access, authentication, and execution of inference tasks via the local shell.
  • [DATA_EXFILTRATION]: User-provided prompt data is transmitted to the inference.sh API to facilitate interaction with selected language models, which is the primary intended function of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 09:10 PM
Security Audit — agent-trust-hub — llm-models