Google has fixed the issues, which exploited a trust boundary between two AI agents with different privileges to potentially ...
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 ...
Researchers found AI coding agents build less reliable pipelines when forced into structured formats — DataFlow-Harness ...
Google removed 3 ADK AI workflows after Pillar showed a public GitHub issue could trigger a privileged agent & reach code ...
Twelve datasets and evaluation systems, built by hand from thousands of real-world security flaws, give model builders and ...
A critical vulnerability in IBM-owned, low-code AI builder Langflow lets unauthenticated attackers execute code remotely on ...
Three Hugging Face Diffusers flaws bypass trust_remote_code, letting crafted model repositories execute code during custom ...
Meta has become the latest AI company to confirm that one of its models hacked a real organization during cybersecurity ...
At Black Hat, Zenity announced new research detailing an active credential-stealing malicious skills campaign distributed through Vercel’s skills.sh.
The Open Secure AI Alliance introduced SAFE guidelines and open agent-security tools at Black Hat, giving enterprises a ...
On 11 July, Hugging Face was subjected to an intense cyberattack from a then-unknown actor. The speed and coordination of the ...
With all the discussion around artificial intelligence, some still view AI as abstract, but make no mistake: Artificial intelligence is the new, and very real, engine that will power our economic and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results