p-image

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill points to installation guidelines hosted on the official inference-sh GitHub repository and recommends the installation of the @belt-sh/cli package. These external resources are required for the skill to interact with the intended image generation service.
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool to perform operations such as user authentication and model inference. The execution is scoped to the belt utility as configured in the skill's frontmatter.
  • [INDIRECT_PROMPT_INJECTION]: User-provided prompts are passed to the belt app run command as part of the JSON input. While this represents a standard ingestion point for untrusted data, it is necessary for the skill's primary function of image generation. No high-risk capabilities were identified that could be exploited through these prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 11:42 AM
Security Audit — agent-trust-hub — p-image