helix-mcp

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

• Third-party content exposure detected (low risk: 0.10). The skill queries the hosted Helix MCP server (https://mcp.helix-db.com/mcp), which returns internal telemetry, query names, planner findings, and recommendation bodies (MDX) generated across cloud workspaces and databases. While these cloud resources and database queries reflect user/developer workloads, recommendation bodies and query names can contain external or untrusted content ingested during execution. However, because the agent must actively select and query specific workspaces/databases rather than monitoring an unvetted public feed or inbound inbox, this falls under low risk.