The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes technical patent data from an external API, creating a vulnerability surface for indirect prompt injection. * Ingestion points: The scripts/utility_patent_detector.py script retrieves data including title, patentAbstract, and claims from the Ruiguan API. * Boundary markers: The instructions do not specify any markers or instructions for the agent to treat this external content as untrusted data. * Capability inventory: The skill possesses the capability to execute shell commands (the Python script), perform network requests, and write files to the file system. * Sanitization: There is no evidence of sanitization or escaping of the patent data before it is presented to the agent for tabular display.
[COMMAND_EXECUTION]: The skill operates by executing scripts/utility_patent_detector.py. This script is designed to manage its own file operations, including creating directories (e.g., nexscope/, .cache/) and writing JSON response files to the current working directory to maintain session records and cache results for 24 hours.

ecommerce-utility-patent-detector