Tag

AI Security

6 AI tools 7 articles
Advertisement
AI tools6
Advertisement
Articles7
AWS Confirms First Production Prompt-Injection Compromise in Bedrock Agents — Enterprise Customer Exfiltrated Documents Cybersecurity 8 min AWS Confirms First Production Prompt-Injection Compromise in Bedrock Agents — Enterprise Customer Exfiltrated Documents In a quietly-published security bulletin, AWS confirmed an indirect prompt-injection attack in production Bedr... CY Cyber Team 18 May EchoLeak: Zero-Click Prompt Injection in Microsoft 365 Copilot Quietly Exfiltrates Enterprise Data Cybersecurity 8 min EchoLeak: Zero-Click Prompt Injection in Microsoft 365 Copilot Quietly Exfiltrates Enterprise Data EchoLeak shows a malicious email can trigger Microsoft 365 Copilot into exfiltrating enterprise data without a... CY Cyber Team 17 May Hackers Reach Anthropic's Restricted Mythos Model Through a Vendor Environment as FSB Calls Briefing Cybersecurity 9 min Hackers Reach Anthropic's Restricted Mythos Model Through a Vendor Environment as FSB Calls Briefing A small group of unauthorised users reached Mythos via a third-party vendor environment on the same day Anthro... CY Cyber Team 17 May Anthropic's Project Glasswing Lines Up AWS, Apple, Google, Microsoft, JPMorgan to Test Mythos for Cyber Defence Cybersecurity 8 min Anthropic's Project Glasswing Lines Up AWS, Apple, Google, Microsoft, JPMorgan to Test Mythos for Cyber Defence Project Glasswing pairs Anthropic's restricted Mythos model with a roster of hyperscalers, banks and the Linux... CY Cyber Team 16 May Microsoft Credits AI With Finding Bugs in May 2026 Patch Tuesday — and the Industry Should Pay Attention AI & ML 12 min Microsoft Credits AI With Finding Bugs in May 2026 Patch Tuesday — and the Industry Should Pay Attention Microsoft's May 2026 Patch Tuesday addressed 118 to 138 CVEs across Windows, Office and Azure — and credited A... AI AI Tools Desk 13 May Anthropic's Project Glasswing Found a 27-Year-Old Bug in OpenBSD — Before Hackers Could Cybersecurity 5 min Anthropic's Project Glasswing Found a 27-Year-Old Bug in OpenBSD — Before Hackers Could Anthropic's Project Glasswing used an unreleased frontier model to find thousands of zero-day vulnerabilities... CY Cyber Team 20 Apr Phishing Attacks Powered by AI Are Now Indistinguishable From Legitimate Emails Cybersecurity 5 min Phishing Attacks Powered by AI Are Now Indistinguishable From Legitimate Emails AI-generated phishing emails are now indistinguishable from legitimate business emails in red team testing. He... CY Cyber Team 5 Apr
Advertisement