The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a bundled Python script scripts/atoms-search.py to retrieve information from a knowledge base. The script is used for data retrieval within the skill's logic.
[EXTERNAL_DOWNLOADS]: The search script connects to api.xyskill.xyz to perform queries when local data is unavailable. This domain is a vendor-controlled resource (xyaz1313) intended for the skill's core functionality.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user video scripts. It includes specific instructions for the agent to extract limited 2-4 word keywords for retrieval rather than processing raw user text, providing a layer of sanitization. The evidence chain includes: (1) Ingestion point: Phase 1 user input, (2) Boundary markers: Absent, (3) Capability inventory: Local script execution via python3, (4) Sanitization: Agent-level keyword extraction logic.

xy-opener