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

p-image

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides links to configuration and installation files hosted on the author's official GitHub repository (inference-sh/skills). These references are neutral and point to the vendor's own infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it processes user-supplied text for image generation.
  • Ingestion points: User-provided image generation prompts are accepted in the --input parameter of the belt CLI examples in SKILL.md.
  • Boundary markers: Prompts are encapsulated within JSON objects passed to the CLI, providing structural separation from the command logic.
  • Capability inventory: The skill is limited to invoking the belt CLI tool for remote image generation via Bash.
  • Sanitization: No specific sanitization is mentioned in the prompt instructions, relying on backend model safety guardrails.
  • [SAFE]: All referenced domains (inference.sh), tools (belt), and repositories are owned by the verified author inference-sh, representing legitimate vendor functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 10:23 AM
Security Audit — agent-trust-hub — p-image