Skills
skills/inference-sh/skills/p-image/Gen Agent Trust Hub

p-image

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected in the skill instructions or metadata.
  • [SAFE]: The skill uses a specific command-line tool (belt) which is correctly restricted in the allowed-tools configuration to prevent arbitrary shell command execution.
  • [SAFE]: All external references, including installation guides and documentation links, point to official vendor resources on the inference.sh domain and their associated GitHub repository.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:48 AM
Security Audit — agent-trust-hub — p-image