generate-image

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION] (SAFE): The script transmits text prompts and base64-encoded image data to https://openrouter.ai/api/v1/chat/completions. This is the intended behavior for an image generation tool and targets a known AI service.\n- [CREDENTIALS_UNSAFE] (SAFE): The script retrieves the OPENROUTER_API_KEY from .env files or environment variables. No hardcoded credentials or unauthorized data exfiltration were detected.\n- [EXTERNAL_DOWNLOADS] (SAFE): The skill identifies a dependency on the standard Python requests library and provides instructions for its installation via pip.\n- [PROMPT_INJECTION] (LOW): The skill has an indirect prompt injection surface as it processes external prompts and images.\n
  • Ingestion points: prompt argument and --input image path in scripts/generate_image.py.\n
  • Boundary markers: Absent; input is placed directly into the API request structure.\n
  • Capability inventory: requests.post for API interaction and local file writing in scripts/generate_image.py.\n
  • Sanitization: No content filtering is performed on the input prompt. This is a low-risk finding inherent to the tool's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:46 PM