image-generation
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill integrates with established services (Google Gemini/Imagen and OpenAI DALL-E) and utilizes official, well-maintained libraries from PyPI (google-genai, openai, pillow, requests).
- [COMMAND_EXECUTION]: Uses the Bash tool as intended to execute Python scripts that perform API calls and image processing tasks.
- [CREDENTIALS_UNSAFE]: Correctly instructs users to manage API keys via environment variables, avoiding the risk of hardcoded secrets.
- [PROMPT_INJECTION]: Instructions focus on legitimate prompt engineering techniques to improve image quality without attempting to override the agent's core safety guidelines or operational constraints.
Audit Metadata