Latest cybersecurity reporting from selected sources.

Microsoft Corp. today released software updates to plug at least 570 security holes in its Windows operating systems and other software, almost triple the number of vulnerabilities the software giant fixed in its record-smashing Patch Tuesday release last month. Microsoft attributed the burgeoning patch counts to vulnerability discoveries aided by artificial intelligence.

Microsoft has unveiled a new multi-model artificial intelligence (AI)-driven system called MDASH to facilitate vulnerability discovery and remediation at scale, adding that it's being tested by some customers as part of a limited private preview

Two recently fixed prompt injections in Salesforce Agentforce and Microsoft Copilot would have enabled an external attacker to leak sensitive data.

Redmond says it's fixed this particular indirect prompt injection vuln Microsoft fixed a security hole in Microsoft 365 Copilot that allowed attackers to trick the AI assistant into stealing sensitive tenant data – like emails – via indirect prompt injection attacks.…

Copilot Falls for Prompt Injection Yet AgainMicrosoft quietly fixed a flaw that allowed users to instruct embedded artificial intelligence model Copilot not to log its access corporate files. "If you work at an organization that used Copilot prior to Aug 18, there is a very real chance that your audit log is incomplete."

Microsoft has fixed a bug causing the March 2025 Windows cumulative updates to mistakenly uninstall the AI-powered Copilot digital assistant from some Windows 10 and Windows 11 systems. [...]

SYSTEM-level command injection via API parameter *chef's kiss* A now-fixed command-injection bug in Kubernetes can be exploited by a remote attacker to gain code execution with SYSTEM privileges on all Windows endpoints in a cluster, and thus fully take over those systems, according to Akamai researcher Tomer Peled.…

Security Researcher Uncovered the Flaw, Which Allowed System TakeoverMicrosoft says it fixed a security flaw in artificial intelligence chatbot Copilot that enabled attackers to steal multifactor authentication code using a prompt injection attack. Security researcher Johann Rehberger said he discovered a way to invisibly force Copilot to send data.

Prompt injection, ASCII smuggling, and other swashbuckling attacks on the horizon Microsoft has fixed flaws in Copilot that allowed attackers to steal users' emails and other personal data by chaining together a series of LLM-specific attacks, beginning with prompt injection.…

Let's take a quick dive into Windows API Microsoft in March fixed an interesting security hole in Outlook that was exploited by miscreants to leak victims' Windows credentials. This week the IT giant fixed that fix as part of its monthly Patch Tuesday update.…