Google has fixed the issues, which exploited a trust boundary between two AI agents with different privileges to potentially ...

Nation-state grade iOS exploit chains Coruna and DarkSword are proliferating among cybercriminals, with 17,000 domains hosting variants.

In what they call the first-ever real-world agent-to-agent exploitation method, Pillar Security researchers say they ...

Autonomous AI cyberattack campaign using DeepSeek and the Hermes Agent framework attacked 460-plus targets after a Chinese ...

Vulnerabilities can lurk within production code for years or decades — and AI tools have opened a gateway to a glut of new long-hidden discoveries. In 2021, a vulnerability was revealed in a system ...

AI vulnerability repair tools can stop exploits yet still produce unsafe fixes. New benchmarks show why rigorous validation ...

Meta is the latest major AI developer to admit that its models broke loose during cybersecurity testing and hacked external ...

AI agent tool bypass vulnerability CoreBreak exposed production agent infrastructure at AWS, Google, and Vercel, where attackers could invoke tools without any model turn. AWS fixed its managed ...

A security researcher claims Kimi K3 discovered a Redis zero-day and produced a proof-of-concept exploit in 27 minutes. Redis has not confirmed the findings.

OpenAI rogue AI agent breach now confirmed at a second company: Modal Labs CTO Akshat Bubna disclosed that the same agent that attacked Hugging Face also exploited a customer's unsecured endpoint.

Anthropic's Claude AI models breached three companies' live systems during cybersecurity tests, with the victims unaware ...

The Open Secure AI Alliance introduced SAFE guidelines and open agent-security tools at Black Hat, giving enterprises a ...