Fooling AI Agents: Web-Based Indirect Prompt Injection Observed in the Wild
Uncover real-world indirect prompt injection attacks and learn how adversaries weaponize hidden web content to exploit LLMs for high-impact fraud. The post F...
Unit 42
3 articles
Threat Brief: March 2026 Escalation of Cyber Risk Related to Iran
Unit 42 details recent Iranian cyberattack activity, sharing direct observations of phishing, hacktivist activity and cybercrime. We include recommendations ...
Taming Agentic Browsers: Vulnerability in Chrome Allowed Extensions to Hijack New Gemini Panel
A high-severity CVE-2026-0628 in Chrome's Gemini allowed local file access and privacy invasion. Google quickly patched the flaw.