nlweb-mcp-server

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches official GitHub documentation and protocol specifications, and web-searches release notes, but does not monitor or consume any untrusted outsider-authored submission channel.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to fetch remote documentation and codebase files from GitHub and modelcontextprotocol.io during setup/runtime, which constitutes unverified remote dependencies.