News
AI Security Is Never Finished: Building the Continuous Red Teaming Loop
1+ hour, 18+ min ago (889+ words) Security programs are built around moments of closure: the finding is closed, the control passed, and the release can move forward. AI security refuses...
From Prompt Testing to AI Red Teaming at Enterprise Scale
3+ week, 1+ hour ago (1199+ words) Anyone can try to break a chatbot. That is part of what makes AI red teaming feel accessible. Open a model, write a strange prompt, ask for something the...
Securing AI Agent Behavior with Amazon Bedrock AgentCore and CheckPoint AI Security
3+ week, 2+ day ago (557+ words) AI agents are rapidly becoming a new operational layer inside the enterprise. Unlike traditional chatbots, modern agents do not simply generate responses....
When Your AI Agent's Memory Becomes a Security Liability
1+ mon, 4+ day ago (42+ words) Key Findings: Check Point Research identified a critical vulnerability chain in LangGraph, an open-source framework from the creators of LangChain that %Check Point Research uncovered a critical LangGraph vulnerability chain that enables remote code execution, exposing AI agent memory, API…...
AI Agents Are Becoming Enterprise Workers. Who Secures Them?
1+ mon, 5+ day ago (1336+ words) AI agents can retrieve data, invoke tools, use credentials, and take action across enterprise workflows. Learn why agentic AI requires runtime security controls for prompts, outputs, data flows, and tool use....
Check Point Frontier AI Models Readiness Program – Security Update
1+ mon, 2+ week ago (353+ words) At Check Point we don’t wait for threats to evolve; we evolve ahead of them. This is why we’ve been running our Frontier AI Models Readiness Program: a proactive, structured initiative designed to ensure that our products remain resilient as…...
From Access Control to Outcome Control: Securing AI Agents with Check Point and Google Cloud
2+ mon, 3+ week ago (474+ words) AI is changing how software works. Applications no longer just process requests. They reason, make decisions, and take action. AI agents now retrieve data, invoke tools, and execute workflows across systems in real time. That shift introduces a new kind…...
ChatGPT Data Leak (Fixed Feb 2026): Key Takeaways
3+ mon, 2+ week ago (771+ words) That assumption was challenged when new research uncovered a previously unknown vulnerability that enabled silent data leakage from ChatGPT conversations without user knowledge or consent. While the issue has since been fully resolved by OpenAI, the discovery delivers a much…...
Check Point Researchers Expose Critical Claude Code Flaws
4+ mon, 2+ week ago (427+ words) The risks fell into three categories. Claude Code includes automation capabilities that allow predefined actions to run when a session begins. Check Point Research demonstrated that this mechanism could be abused to execute arbitrary shell commands automatically upon tool initialization....
Opening the Automation Garden: API Request & Webhook Trigger in Infinity Playblocks
6+ mon, 6+ day ago (457+ words) Today’s security teams work in complex, multi-tool environments. Alerts flow from SIEMs, tickets are created in ITSM platforms, actions occur in cloud and network controls, and workflows span countless third-party services. To keep pace, automation must be open, flexible, and…...