skills/skills-101/superpowers/p-image/Gen Agent Trust Hub

p-image

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and installs tools from the inference-sh GitHub organization and uses npx to add related skills such as belt-sh/cli. These are official resources for the inference.sh platform.- [COMMAND_EXECUTION]: The skill uses the belt CLI tool to perform model inference and application management. The commands provided are standard for the inference.sh service and are restricted to model interaction.- [DATA_EXPOSURE]: Documents the standard platform authentication procedure using belt login. No unauthorized access to local sensitive files or hardcoded credentials were detected.- [PROMPT_INJECTION]: The skill accepts user-supplied prompts and image URLs as input for image generation. While this is an indirect prompt injection surface, it is the primary intended functionality of the service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 08:29 PM
Security Audit — agent-trust-hub — p-image