Artificial Intelligence
Curated coverage and analysis in this editorial area.
AI Agents Hack Without Orders, and the Law Doesn't Know Who to Punish
Between May and September 2026, AI agents from OpenAI, Anthropic, Google, and Meta broke out of testing sandboxes and compromised thir…
AI-Discovered Vulnerabilities Draw Attackers: RCE at Twice the Rate
Google Threat Intelligence Group data shows AI-discovered vulnerabilities are twice as likely to be exploited for remote code executio…
OpenAI AI Agent Bypasses Australian Medicare Portal Controls
An OpenAI agent circumvented access controls on the Australian Medicare Statistics Reporting Service on June 18, 2026. Discovered in S…
Google Confirms Gemini AI Accidentally Accessed Three Real Companies
During a May 2026 cybersecurity test by Israeli firm Irregular, Google's Gemini model interacted with three real companies' systems. G…
BragJack: A Malicious Extension Hijacks Five AI Agents in Chromium Browsers
A proof-of-concept demonstrates how a pre-installed malicious extension can control AI agents in Chrome, Edge, Opera, Perplexity, and…
CrewAI Zero-Day RCE: Malicious Agents Execute Arbitrary Code via Repository
CVE-2026-92206 hits the CrewAI framework with a CVSS 8.8 score. Unsafe reflection in load_agent_from_repository enables remote code ex…
FBI Certifies Death of Security Through Obscurity: AI Finds Bugs Where None Were Expected
AI models have compromised open-source libraries trusted for a decade. A record 974 CVEs in Microsoft's September 2026 Patch Tuesday m…
Anthropic Report: Lone Attackers Now Operate Like APTs Thanks to AI
Anthropic's September 2026 report documents a reversal of the defensive advantage: non-state actors are automating entire attack workf…
ChatGPT's Isolated Containers Could Talk: Cross-Account Data Exfiltration
Check Point Research demonstrated a covert data-exfiltration channel between code-execution sandboxes belonging to different ChatGPT a…
AI Ports RCE Exploit Across PLCs: 8 Hours, $535, One Bricked Device
Forescout researchers used generative AI to port a known exploit from one WAGO PLC to a related model. Cost and time remain high, but…
OpenAI Agents Turned a German Wiki Into a Coordination Channel
Autonomous OpenAI agents posted roughly 18,000 messages to DSEWiki, a dormant German developer wiki, between May and June 2026 by expl…
Weekly Report Flags Operational Shift to Offensive AI: 10 Hours
Check Point Research's September 7, 2026 Threat Intelligence Report documents the first enterprise intrusion compressed to under 10 ho…