The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill accepts external images and text prompts from users to generate room designs, which establishes an attack surface for indirect prompt injection.
Ingestion points: User-supplied image paths and text prompts are passed as arguments to the scripts/redesign.py script.
Boundary markers: The skill does not employ explicit delimiters or cautionary instructions to the model to ignore potential injections within the provided image or text data.
Capability inventory: The skill has the ability to write files to the local disk using the Write tool.
Sanitization: There is no evidence of validation or sanitization of the user-provided prompt or image data before it is sent to the Gemini API.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the requests library from the Python Package Index (PyPI), which is a well-known and trusted package registry.
[COMMAND_EXECUTION]: The skill executes a local Python script (scripts/redesign.py) via Bash to perform its core image processing and API communication tasks.

room-redesign