The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/connections.py and scripts/evaluation.py scripts enable the execution of local shell commands via the stdio transport to launch and manage MCP servers during testing.
[EXTERNAL_DOWNLOADS]: The SKILL.md file directs the agent to fetch protocol specifications and SDK documentation from official sources, including modelcontextprotocol.io and the modelcontextprotocol GitHub organization.
[PROMPT_INJECTION]: The scripts/evaluation.py script identifies an indirect prompt injection surface by ingesting test questions from XML files and interpolating them into the LLM context. This is documented as an inherent risk of the evaluation framework that requires developer oversight.
[DATA_EXFILTRATION]: The skill provides tools for connecting to remote service endpoints via HTTP and SSE as part of the MCP standard, which is necessary for integrating external APIs.

mcp-builder