not-human-search-mcp

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

• Third-party content exposure detected (low risk: 0.10). The agent searches and inspects third-party indexed websites and tool metadata via search tools and domain inspection, representing low-risk external content ingestion.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill configures a remote third-party MCP server URL (https://nothumansearch.ai/mcp) from an unverified community publisher, constituting a weak operational dependency.