not-human-search-mcp

Warn

Audited by Snyk on Apr 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill queries the remote Not Human Search MCP which indexes 1,750+ public AI-ready websites and returns site details/endpoints (see SKILL.md tools like search_agents, get_site_details, verify_mcp and submit_site), so the agent ingests untrusted third-party site data that can influence subsequent tool discovery and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 18, 2026, 03:48 PM
Issues
1