AI Security Cybersecurity News

Latest News

ChatGPT Lockdown Mode Bypassed: Researchers Demonstrate Silent Chat Exfiltration

ChatGPT Lockdown Mode Bypassed: Researchers Demonstrate Silent Chat Exfiltration

RedSide Security November 06, 2026 AI Security 166 views

Researchers found and disclosed a now-patched flaw that bypassed ChatGPT's Lockdown Mode, allowing silent chat data exfiltration without user interaction — highlighting the persistent challenge of prompt-injection defense.

Continue reading: ChatGPT Lockdown Mode Bypassed: Researchers Demons…
OpenAI's AI Pipeline Generates 948 Linux Root Escalation Exploits in 30-Hour Run

OpenAI's AI Pipeline Generates 948 Linux Root Escalation Exploits in 30-Hour Run

RedSide Security November 05, 2026 AI Security 245 views

OpenAI's prototype AI pipeline validated and patched 948 Linux local privilege escalation vulnerabilities in a 30-hour run, costing $1.2 million in API fees—raising dual-use concerns.

Continue reading: OpenAI's AI Pipeline Generates 948 Linux Root Esca…
Researchers Flag 'Prompt Adware' Hidden Inside OpenAI Codex Jailbreak Toolkit

Researchers Flag 'Prompt Adware' Hidden Inside OpenAI Codex Jailbreak Toolkit

RedSide Security November 05, 2026 AI Security 233 views

Check Point Research has detailed Haiou, an OpenAI Codex jailbreak bundle that modifies the agent's configuration to inject ads for a third-party AI gateway — a technique dubbed prompt adware.

Continue reading: Researchers Flag 'Prompt Adware' Hidden Inside Ope…
Anthropic's Unreleased AI Model Chains Zero-Days Into Working Exploits Across Chrome, Safari, Windows, and Linux

Anthropic's Unreleased AI Model Chains Zero-Days Into Working Exploits Across Chrome, Safari, Windows, and Linux

RedSide Security October 28, 2026 AI Security 303 views

An unreleased Anthropic AI model identified flaws in Chrome, Safari, Android, Windows, and Linux and chained them into working proof-of-concept exploits in a lab setting—all reported to vendors and already patched.

Continue reading: Anthropic's Unreleased AI Model Chains Zero-Days I…
AI Agents Breach Anthropic's Internal Systems in Under 12 Hours

AI Agents Breach Anthropic's Internal Systems in Under 12 Hours

RedSide Security October 26, 2026 AI Security 309 views

Security startup Cathedral says its AI agents found routes into Anthropic's internal business systems in under 12 hours during an authorized researcher program, highlighting how fast automated tooling can chain flaws across connected services.

Continue reading: AI Agents Breach Anthropic's Internal Systems in U…