Skills
skills/inference-sh/agent-skills/ai-image-generation/Gen Agent Trust Hub

ai-image-generation

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the use of the infsh CLI for AI image generation. The execution environment is appropriately restricted via the allowed-tools configuration, which limits shell access specifically to the infsh command set.
  • [EXTERNAL_DOWNLOADS]: The documentation provides links to installation scripts and related resources hosted on the vendor's official GitHub repository (github.com/inference-sh/skills). These are standard operational resources for the service.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by interpolating user-provided prompts into CLI command arguments.
  • Ingestion points: User-supplied prompt strings used in the infsh app run commands.
  • Boundary markers: Prompts are contained within JSON-formatted strings passed as command-line arguments.
  • Capability inventory: The infsh tool performs network requests to external APIs to process images.
  • Sanitization: No explicit sanitization or input validation is specified within the instructions; the skill relies on the underlying platform's handling of command-line arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 08:16 PM