These 4 critical AI vulnerabilities are being exploited faster than defenders can respond

From prompt injection to deepfake fraud, security researchers say several flaws have no known fix. Here's what to know about them.
Axios on MSN

Anthropic's newest AI model uncovered 500 zero-day software flaws in testing

Anthropic's latest AI model has found more than 500 previously unknown high-severity security flaws in open-source libraries ...
WDAF-TV

OWASP GenAI Security Project Releases Top 10 Risks and Mitigations for Agentic AI Security

Culmination of over 100 industry leaders' input and extensive published resources to deliver critical guidance to address Agentic AI Security risks WILMINGTON, Del., Dec. 10, 2025 /PRNewswire/ -- The ...
Forbes

The Risks Of Third-Party AI Reliance: How To Prevent Vulnerability

Expertise from Forbes Councils members, operated under license. Opinions expressed are those of the author. The launch of GPT-5 on August 7, 2025, and the immediate removal of GPT-4o from ChatGPT’s ...
CSOonline

Managing agentic AI risk: Lessons from the OWASP Top 10

Agentic AI is being adopted fast by enterprises, propelled by an explosion of use cases, but security, as always, is lagging. The OWASP Top 10 for Agentic AI can help close that gap. LLM-powered ...
Security Boulevard

How is Agentic AI changing healthcare security

How Does Agentic AI Revolutionize Healthcare Security? Are you prepared to explore the transformative power of Agentic AI in securing the healthcare industry? The intersection of artificial ...