Please turn on your JavaScript for this page to function normally.
prompt injection
Stealthy attack serves poisoned web pages only to AI agents
AI agents can be tricked into covertly performing malicious actions by websites that are hidden from regular users’ view, JFrog AI architect Shaked Zychlinski has found. …
Microsoft: “Hack” this LLM-powered service and get paid
Microsoft, in collaboration with the Institute of Science and Technology Australia and ETH Zurich, has announced the LLMail-Inject Challenge, a competition to test and improve …
Featured news
Resources
Don't miss
- Hackers used Cisco zero-day to plant rootkits on network switches (CVE-2025-20352)
- Microsoft revokes 200 certs used to sign malicious Teams installers
- A new approach to blockchain spam: Local reputation over global rules
- SAP zero-day wake-up call: Why ERP systems need a unified defense
- “Perfect” Adobe Experience Manager vulnerability is being exploited (CVE-2025-54253)