Critical out-of-bounds read in Ollama before 0.17.1 leaks process memory including API keys from over 300000 servers via ...
New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...
The attacks compromise aerospace and drone firms' systems to exfiltrate GIS files, terrain models, and GPS data to gain a clear picture of analysts' intel.
Frontier AI models corrupt 25% of document content in multi-step workflows — rewriting rather than deleting, which makes the ...
The popular Python package for monitoring data quality was briefly available as a malicious version. Provider Elementary ...
Hermes Agent’s latest release shows how AI agents are evolving from assistants into self-improving tools that learn, build, ...
TanStack had 2FA, OIDC publishing, and Sigstore provenance on every release. The Mini Shai-Hulud worm published 84 malicious ...
Fake OpenAI Privacy Filter hit #1 on Hugging Face with 244,000 downloads, spreading infostealer malware to Windows users.
Our '7 Days' weekly tech roundup brings the juiciest announcements. Read about Edge browser handling passwords in plaintext, JDownloader getting hacked, and the TAB key.
In the latest evolution of automated cyberattacks, 2 threat campaigns heavily leveraged AI agents to support attacks against ...
The 2FA bypass exploit stemmed from a faulty trust assumption, providing evidence of AI reasoning that can discover ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results