The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script skills/shared/scripts/image_ops.py with various subcommands such as resize, crop, pad, convert, compress, watermark, round, collage, thumbnail, and info to perform image manipulation as defined in SKILL.md. \n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied image files, which represents an ingestion point for potentially malicious data that could influence agent behavior if metadata or content is interpreted. \n
Ingestion points: User-provided image file paths are passed via the -i parameter to the image_ops.py script. \n
Boundary markers: There are no explicit instructions or delimiters defined to isolate the content of the processed images from the agent's control flow. \n
Capability inventory: The skill performs subprocess execution of the image_ops.py script for all its primary functions. \n
Sanitization: No validation or sanitization of the image content or metadata is specified in the instructions.

image-editing