AI Image Generation
Pass
Audited by Gen Agent Trust Hub on Jun 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill's setup instructions utilize basic shell commands (
mkdir,test) to initialize a local configuration directory at~/image-generation/and verify the existence of environment variables. These are standard operations for environment configuration. - [EXTERNAL_DOWNLOADS]: The skill provides integration patterns and documentation for several well-known AI services, including OpenAI, Google Gemini/Vertex AI, Black Forest Labs, Replicate, Leonardo AI, and Ideogram. It also recommends the installation of industry-standard Python libraries such as
diffusers,transformers,torch, andreplicatefor image processing tasks. - [CREDENTIALS_UNSAFE]: Authentication is handled via environment variables (e.g.,
OPENAI_API_KEY,BFL_API_KEY), and the skill documentation explicitly advises users against sharing secret values in the chat interface. No hardcoded credentials or unsafe secret management practices were found. - [DATA_EXFILTRATION]: Network communication is directed solely toward the official API endpoints of the documented AI providers for the legitimate purpose of generating and editing images based on user prompts.
Audit Metadata