generate-image

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-controlled data into requests sent to an external AI model.
  • Ingestion points: The skill accepts user-provided text prompts and local image files via the prompt and --input arguments in scripts/generate_image.py.
  • Boundary markers: No delimiters, structured formatting, or protective instructions are utilized to isolate user input from the request logic.
  • Capability inventory: The scripts/generate_image.py script is capable of reading local files, writing generated images to the filesystem, and performing network operations to the OpenRouter API endpoint.
  • Sanitization: No sanitization, validation, or filtering of the prompt text or image content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 08:47 PM