p-image
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions and additional components from the author's official GitHub repository (inference-sh/skills).
- [COMMAND_EXECUTION]: The skill employs the
beltCLI tool, as defined in its allowed tools, to communicate with the Pruna image generation service for processing text-to-image and image-editing requests. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text prompts for image generation. This represents the primary functionality of the tool; the processing of this untrusted data is managed by the external API and the agent's internal safety guardrails.
Audit Metadata