skills/halt-catch-fire/skills/p-image/Gen Agent Trust Hub

p-image

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI for all core operations. It appropriately uses the allowed-tools field in the frontmatter (Bash(belt *)) to restrict the agent's shell environment to only that specific command, minimizing the potential attack surface.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation guides from the official inference.sh website and its associated GitHub repository (inference-sh/skills). These resources originate from a well-known technology service and are used as intended for tool configuration and usage guidance.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:15 AM
Security Audit — agent-trust-hub — p-image