Check Point PromptGuardX: Securing the Files AI Agents Trust
Check Point, Tuesday, October 6th, 2026
Check Point PromptGuardX scans PDFs for hidden prompt-injection instructions before their content reaches an LLM or AI agent.
Check Point introduced PromptGuardX, which moves prompt-injection detection into the file layer as part of its AI Defense Plane.
Integrated into Check Point Threat Emulation, it analyzes PDF files before their content reaches an LLM, copilot or AI agent, catching hidden instructions in invoices or contracts that are clean from a malware perspective.
Such instructions can otherwise trigger an agent's tools, APIs and permissions, so PromptGuardX adds an upstream layer alongside prompt inspection, runtime monitoring, access controls and action-level enforcement.