Înapoi la articole →

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 10
  1. An active malware campaign used typosquatted skills, trojanized packages, and remote loaders to target users of popular AI tools.

  2. We spent the last 6 months building a global network of honeypots with exposed AI inference and agent endpoints.

  3. Give Us Your Taste

    AI is incredible.

  4. Yesterday (Feb 17, 2026, 12:18AM ET) Cline released an advisory about an unauthorized npm publication.

  5. Edit (2/19 2:30AM ET): This blog post was written during an ongoing investigation.

  6. Over the past year I’ve been asking people the same question over and over again: when our AI systems are targeted, will you know?

  7. I gave a talk at the AI Agent Security Summit by Zenity Labs on October 8th in San Francisco.

  8. Enterprise systems provide a terrible user experience.

  9. We’re getting asks for more info about the 0click AI exploits we dropped this week at DEFCON / BHUSA.

  10. AWS security blog confirms the attacker gained access to a write token and abused it to inject the malicious prompt.