The Agent Skills Directory

[COMMAND_EXECUTION] (LOW): The scripts/connections.py file contains the MCPConnectionStdio class, which uses the mcp library to spawn subprocesses using arbitrary commands and arguments. While this is the intended mechanism for MCP stdio servers, it provides a high-privilege execution capability that could be targeted by an attacker.
[EXTERNAL_DOWNLOADS] (LOW): The SKILL.md file directs the agent to fetch documentation from modelcontextprotocol.io and GitHub. These are non-whitelisted external sources used to provide context for the agent's tasks.
[PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) due to the combination of external data ingestion and powerful tool capabilities.
Ingestion points: External markdown documentation is fetched from the web as part of the implementation workflow.
Boundary markers: None; the skill does not define specific delimiters or instructions to ignore embedded commands in the fetched documentation.
Capability inventory: The connections.py script enables local command execution via stdio and network communication via SSE and HTTP transports.
Sanitization: None; there is no evidence of sanitization or content validation for the externally retrieved documentation.

mcp-builder