Suspected Ransomware Operator Used Claude Code to Steal Data and Map Backups
Gambit observed Claude Code inside six intrusions. Hunt the test VPN account, rogue LDAP listeners, backup discovery, SQL staging, and firewall restores.
Read article →AI
AI systems, model security, agent abuse, and attacks that use generative tools.
CISA Flags Exploited Ray Flaw That Runs Code Through Firefox and Safari
A hostile page can rebind its hostname to a Ray dashboard, change Firefox or Safari's User-Agent header, and submit a shell command to the Jobs API.
Read article →
Stolen AI API Key Leaves One Company With Nearly $1 Million Bill
Unit 42 says stolen AI API keys can reach gray-market proxy services within minutes, turning one exposed credential into catastrophic usage charges.
Read article →
Hidden VS Code MCP Settings Let Install Links Run Attacker Code
CVE-2026-41613 let crafted MCP install links persist settings that the VS Code preview did not show. Version 1.119.1 fixes the preview.
Read article →
Chrome Fixed 1,072 Bugs, Then Changed How Updates Reach Users
Chrome fixed more security bugs in two milestones than in the previous 23 while using AI across discovery, triage and fix preparation.
Read article →
Claude Breached Three Organizations During Anthropic Cyber Tests
A misconfigured evaluation harness let three Claude models reach production systems, exposing a control gap that prompts and model safeguards could not contain.
Read article →
Hermes Logs Record File Enumeration on a Thai Finance Ministry System
Five recovered task logs record service discovery, privilege checks and file enumeration after an operator enabled Hermes's unattended mode.
Read article →
OpenAI Cyber Test Breached Hugging Face Production
Hugging Face traced 17,600 actions from an Artifactory escape through two malicious-dataset vectors and into its clusters, network and source control.
Read article →
Crafted ChatGPT Link Created a Scheduled Workspace Agent in Tests
Zenity found URL parameters that preselected a template and auto-submitted instructions inside a logged-in user's Workspace Agents builder.
Read article →
CISA Confirms Exploitation of LiteLLM MCP Preview Command Injection
Any authenticated proxy-key holder could make two MCP preview endpoints run an arbitrary command on the LiteLLM host.
Read article →
Search Ads Used Real ChatGPT Pages to Deliver Malware
Push Security traced paid search ads to shared ChatGPT and Claude pages that handed visitors to fake desktop-app downloads.
Read article →
Google Sued a Phishing Service Behind 2.5 Million Scam Texts
A civil lawsuit targets a Telegram-based phishing-kit operation that Google links to 2.5 million texts and more than one million fraudulent URLs.
Read article →
GhostCommit Hid Secret-Theft Instructions Inside a PNG
Researchers put instructions to read .env and encode it into source inside a PNG that text-only pull-request reviewers ignored but vision-capable coding agents later followed.
Read article →Showing 27–39 of 47