Salt Security adds native AI Detection and Response (AI-DR) to its Agentic Security Platform

On Sept 22, 2026 Salt Security extended its Agentic Security Platform with native AI-DR inside AG-DR, giving real-time detection of direct/indirect prompt injection, jailbreak attempts and unsafe model behavior, correlated downstream across MCP servers, tools and APIs.

Closes the gap that typically splits LLM-layer protection (guardrails) from API/agent runtime telemetry — security teams can now see a full attack chain from model to downstream systems in one view.

Enterprises running agentic AI on MCP/API ecosystems with existing Salt AG-DR/AG-SPM deployments should enable the new AI-DR runtime capabilities.