llm-models

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or safety bypass attempts were detected within the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill directs users to install dependencies and view documentation from the vendor's official domain (inference.sh) and GitHub organization (inference-sh). These resources are consistent with the skill's purpose.
  • [COMMAND_EXECUTION]: Shell access is strictly limited to the belt CLI tool using the allowed-tools frontmatter restriction. This follows the principle of least privilege, preventing arbitrary command execution.
  • [DATA_EXPOSURE]: The skill does not access sensitive local files or hardcode credentials. It uses a standard login flow via the CLI tool for authentication.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:15 AM
Security Audit — agent-trust-hub — llm-models