The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run a local script scripts/image_treat.py for batch processing images. This is a legitimate functional requirement of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data (images) which could potentially contain malicious payloads.
Ingestion points: The scripts/image_treat.py script reads files from an input directory specified via the src argument.
Boundary markers: None explicitly present for binary image data.
Capability inventory: The script performs file reads, image manipulations (crop, grade, grain), and file writes to an output directory. It does not perform network operations or subprocess execution.
Sanitization: The script uses os.path.basename when constructing output file paths, mitigating simple path traversal attacks on the output side.

visual-assets