not-human-search-mcp
Warn
Audited by Snyk on Aug 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the agent uses the Not Human Search MCP server toolchain to search/inspect/verify specific external sites (e.g., via
search_agentsandget_site_details) based on user-provided keywords/domains, which can lead the LLM to ingest outsider-authored text from those fetched site details at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata