The Agent Skills Directory

Dynamic Execution (MEDIUM): The MCPConnectionStdio class in scripts/connections.py uses mcp.client.stdio.stdio_client to execute system commands. The command and args parameters are passed directly to a subprocess. If these values are derived from untrusted prompt interpolation or external data, it could lead to arbitrary command execution on the host environment.
External Downloads & Network Access (MEDIUM): The MCPConnectionSSE and MCPConnectionHTTP classes in scripts/connections.py allow the agent to establish network connections to arbitrary URLs. This capability could be abused for data exfiltration or to connect to malicious external servers.
Indirect Prompt Injection (LOW): The skill is designed to ingest and process data from external MCP servers without apparent sanitization or boundary markers.
Ingestion points: Data enters through the call_tool method in scripts/connections.py which retrieves content from external tool executions.
Boundary markers: Absent. There are no delimiters or instructions to ignore embedded commands in the tool output.
Capability inventory: The skill includes high-privilege capabilities such as subprocess spawning (stdio_client) and network communication (sse_client, streamablehttp_client).
Sanitization: Absent. Output from external tools is returned as-is to the calling agent.

mcp-builder