The Agent Skills Directory

[SAFE]: The skill utilizes the official google-genai library to interact with Google's Gemini API, which is a well-known and trusted service provider.
[SAFE]: Credential management follows best practices by using environment variables (GEMINI_API_KEY) or command-line arguments instead of hardcoding sensitive tokens.
[COMMAND_EXECUTION]: The skill operates by executing a local Python script through the uv tool as part of its primary functionality for image processing.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface common to tools that process external media and user-provided instructions.
Ingestion points: The skill reads external image files and text prompts via command-line arguments in scripts/generate_image.py.
Boundary markers: The script does not utilize specific delimiters to isolate user-provided data from the instructions passed to the generative model.
Capability inventory: The skill is capable of performing network operations (via the Gemini API) and writing generated PNG files to the local file system.
Sanitization: There is no explicit sanitization of the input image metadata or prompt text within the skill's scripts.

nano-banana-pro