p-image
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements the principle of least privilege by using the
allowed-toolsfrontmatter to restrict the agent's execution environment to only allow shell commands starting withbelt. - [SAFE]: All external links point to official vendor domains (
inference.sh) or the vendor's public GitHub repository (github.com/inference-sh) for legitimate documentation and setup instructions. - [SAFE]: The skill does not contain any hidden instructions, hardcoded credentials, or attempts to access sensitive system files.
- [SAFE]: Interactions with the CLI tool use structured JSON inputs for model parameters, which is a standard and safe practice for this type of integration.
Audit Metadata