Claude Max Giveaway Fakes a Google Window to Steal Logins
A fake Claude Max gift draws its own Google sign-in window. See…
CLOSEDQUORUM: Windows Malware Puts Its Next Move to a Vote
Talos found a Windows implant designed to take votes from four AI…
Talking Tilly: The Camera Keeps Analysing After the Age Check
Talking Tilly requires an age selfie, analyses mood during calls and keeps…
AgentCore Harness Test Exposes a Service Token Through Memory
Unit 42 demonstrated AgentCore credential theft through a support ticket. See why…
AI Access Thief Sends 43 KB of Agent Context to a Honeypot
An attacker’s coding agent exposed instructions, keys and history to a research…
Claude Sessions Stolen by Infostealers Drain Usage
Anthropic warns that infostealers are stealing Claude sessions and draining usage. Learn…
OpenAI Exposes Russian Influence Campaign Behind Fake Think Tank
OpenAI banned accounts very likely operated from Russia that promoted a fake…
Grok Cryptographic Context Injection Could Leak Chat History
Adversa AI showed how encrypted webpage instructions could make Grok expose current-chat…
LiteLLM Breach May Have Exposed 2,500+ Organizations
CloudSEK maps 2,500+ organizations in a LiteLLM exposure dataset. Check versions 1.82.7…
OpenAI Agent Hacked Hugging Face—and Went Unnoticed for Days
An OpenAI evaluation agent reached Hugging Face production while pursuing benchmark answers.…
Grok Build Repository Upload: What to Do After Version 0.2.93
Grok Build 0.2.93 was observed uploading tracked repositories and Git history. Here…
Antigravity language_server.exe Malware Warning: Safe to Restore?
Antigravity 2.3.1 language_server.exe hash verified. Check the source, path, version, SHA-256, and…