The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided classification and filtering requirements to generate implementation advice.\n
Ingestion points: Expected Inputs including classification requirements, hierarchy structure, and delivery-side query needs defined in SKILL.md.\n
Boundary markers: The skill does not implement specific data delimiters to encapsulate user input, although it provides general behavioral instructions to the agent regarding safety.\n
Capability inventory: The skill is permitted to use Read, Grep, and Glob tools to analyze project files as part of its advisory function (SKILL.md).\n
Sanitization: No specific input validation or sanitization mechanisms are described for the data processed at runtime.

cms-taxonomy