Skills
Navigate
skills/seaworld008/commonly-used-high-value-skills/native-mcp/Gen Agent Trust Hub

native-mcp

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill enables connection to external MCP servers that register tools and can request LLM sampling (agentic loops). This creates a vulnerability surface where a compromised or malicious server could provide tool outputs or sampling requests designed to influence the agent's behavior.
  • [EXTERNAL_DOWNLOADS]: Instructs users to install the official mcp Python SDK from PyPI using pip or uv.
  • [COMMAND_EXECUTION]: Provides examples for executing MCP servers through system commands like npx and uvx to enable directory access, time utilities, and GitHub integrations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:54 AM
Security Audit — agent-trust-hub — native-mcp