gpt-image-1-5
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes official and well-known libraries (openai, pillow) for its primary functionality.
- [SAFE]: The code implements standard image processing and API communication without any hidden or malicious behaviors.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted user prompts and image files. Ingestion points: User-provided values for "--prompt" and file paths for "--input-image" in "scripts/generate_image.py"; Boundary markers: The skill does not employ boundary markers or instructions to disregard potential instructions within inputs; Capability inventory: "scripts/generate_image.py" possesses capabilities for file system access (read/write) and network operations (OpenAI API); Sanitization: No input validation or content sanitization is performed on the provided prompts or images.
Audit Metadata