The Agent Skills Directory

[SAFE]: The skill follows its stated purpose of generating a CAP-related trivia quiz without any hidden or malicious behaviors.
[COMMAND_EXECUTION]: The skill utilizes legitimate MCP tools (cds-mcp_search_docs and question) to perform its functions. The search queries are contextually appropriate for the CAP model, and the use of the question tool for UI interaction is a standard practice.
[PROMPT_INJECTION]: The instructions do not contain patterns aimed at bypassing safety filters or overriding the agent's core instructions.
[DATA_EXFILTRATION]: There is no evidence of sensitive file access or network operations to non-whitelisted domains. The skill only processes data retrieved from CAP documentation to create educational content.

cap-trivia