AutoJack Attack: One Malicious Web Page Can Hijack AI Agents for Remote Code Execution
Microsoft researchers have disclosed a novel exploit chain named AutoJack that allows a single malicious web page to hijack an AI browsing…
Microsoft researchers have disclosed a novel exploit chain named AutoJack that allows a single malicious web page to hijack an AI browsing…
AutoGen is a framework developed by Microsoft for building multi-agent AI systems. It allows developers to create and manage multiple AI agents…
Another command injection vulnerability in Microsoft Semantic Kernel related to insecure shell command handling.
A vulnerability in Microsoft's Semantic Kernel agent framework where model output reaching a shell can lead to command injection. Patched by Microsoft.
GitHub has announced a critical security update to its official actions/checkout action, effective June 18, 2026, designed to block common pwn request…
Microsoft's Azure Sentinel was found to have a CI/CD workflow weakness that allowed unauthenticated attackers to run code and steal credentials via…
Cybersecurity researchers at Novee Security have identified a critical exploitable pattern in CI/CD workflows, codenamed Cordyceps, that allows unauthenticated attackers to hijack…
A coordinated international law enforcement operation, supported by private sector partners including Bitdefender, Bitsight, ESET, and Microsoft, has successfully dismantled the criminal…
Microsoft was identified as a relevant cybersecurity entity in recently ingested reporting. This profile is generated so related cyber news, CVEs, malware,…
Microsoft Windows Buffer Overflow Vulnerability Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of…