The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided concept descriptions and interpolates them into prompt templates retrieved from its local database.
Ingestion points: The concept argument in scripts/generate.py and scripts/search.py serves as the entry point for untrusted user data.
Boundary markers: The prompt templates in data/awesome-prompts.csv and data/nano-banana-templates.csv do not utilize explicit delimiters or instructions to prevent the model from following instructions embedded within the user's concept description.
Capability inventory: The skill possesses the capability to make network requests to the Gemini API and write image files to the local file system.
Sanitization: The adapt_prompt function in scripts/generate.py uses regex for placeholder replacement but does not perform sanitization, escaping, or validation of the user's input before interpolation.
[DYNAMIC_EXECUTION]: The execution scripts scripts/generate.py and scripts/search.py modify the Python module search path (sys.path) at runtime. This allows the skill to load environment resolution utilities and other scripts from the user's home directory (~/.claude/scripts) and parent project directories, which is a characteristic of the targeted execution environment.
[EXTERNAL_DOWNLOADS]: The skill depends on the google-genai library to facilitate communication with Google's image generation models.

ai-artist