setup-gbrain

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly wires a gbrain instance to index and query third-party hosts (e.g., GitHub/GitLab artifacts in Step 7 and remote gbrain MCP URLs in Path 4) and the preamble's gstack-brain-context-load renders gbrain query results into the agent's preamble so the model will read and act on untrusted/user-generated repo/web content.