Eurostar AI chatbot flaws let attackers alter history, leak prompts
TL;DR A security researcher found multiple weaknesses in Eurostar's public AI chatbot that allowed guardrail bypass, prompt exfiltration and client-side…
Eurostar chatbot flaws exposed: guardrail bypass, injections and signatures
TL;DR A security researcher found multiple weaknesses in Eurostar’s public AI chatbot, including guardrail bypasses, unchecked message and conversation IDs,…
Palo Alto exec warns AI agents will be 2026’s leading insider threat
TL;DR Palo Alto Networks' security-intel chief Wendi Whitmore says task-specific AI agents will emerge as a major insider threat in…
Cybersecurity tabletop exercises adapt to AI threats and analog defenses
TL;DR Security teams are revising end-of-year tabletop exercises to reflect attackers' growing use of AI and the need to protect…
Pen testers say Eurostar accused them of ‘blackmail’ after chatbot flaws
TL;DR Security researchers at Pen Test Partners reported four vulnerabilities in Eurostar's public AI chatbot that could enable prompt injection,…
Cybersecurity Forecast 2026: Preparing Organizations for Emerging Threats
TL;DR Google Cloud published its Cybersecurity Forecast 2026 report on November 4, 2025, synthesizing frontline data and expert analysis to…
Former spy and startup CEO predicts a ‘WannaCry of AI’ is imminent
TL;DR Sanaz Yashar, a former Unit 8200 operative and current CEO of Zafran Security, warns that AI is accelerating the…
OpenAI: Agentic AI browsers will likely remain vulnerable to prompt injection
TL;DR OpenAI acknowledges that prompt injection attacks are a persistent risk for agentic AI browsers like ChatGPT Atlas and says…