image-generation

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a Python script to execute image generation tasks via the OpenAI API.
  • [EXTERNAL_DOWNLOADS]: The script downloads image data from OpenAI's API and associated image hosting URLs.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
  • Ingestion points: The prompt argument in generate_image.py.
  • Boundary markers: None.
  • Capability inventory: File system writing to a specified directory and network access to the OpenAI API.
  • Sanitization: None. This surface is characteristic of image generation tools and represents a low risk.
  • [SAFE]: Sensitive data is managed through environment variables rather than hardcoded secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 02:24 AM