Stop Common Prompt Injection Phrases (v1) in xAI (Grok) Traffic

AI security governance · MCP security · LLM gateway

What it does

Keyword-based detection of frequently observed prompt-injection phrases. v2 (ML-backed) is planned in the future-tasks file.

How Igris secures xAI (Grok) traffic

Igris Content Guard inspects xAI (Grok) requests and responses for Common Prompt Injection Phrases (v1) using keywords-based detection, then blocks matches.

Gateway config for xAI (Grok)

// Igris gateway → xAI (Grok)
baseUrl: "https://api.x.ai/v1"
contentGuard:
  detectors: ["openai-injection-v1"]
  action: "deny"

Other detectors for xAI (Grok)

Secure your AI estate with Igris