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.
Reader edition
The Feed
Static Cisco Secure FMC Account Is Under Active Exploitation
Every on-prem Secure FMC configuration is affected. Cisco published hot fixes, a shared license.tmp indicator, and credential-rotation guidance.
Compromised Microsoft 365 Mailboxes Spread QR-Code Phishing
Talos tied QR-code PDFs to credential theft, inbox-rule changes, SharePoint staging and new phishing sent from compromised Microsoft 365 mailboxes.
Mirage Kitten Used Compromised Windows Hosts as Network Relays
Kaspersky found BridgeHead using Windows SSO to cross corporate proxies before relaying server-selected TCP traffic through compromised hosts.
Fastjson Flaw Enabled RCE in Spring Boot Fat JAR Applications
The flaw reaches an unsafe resource-loading path without AutoType enabled. Exposure is limited to a specific Fastjson 1.x and Spring Boot deployment combination.
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.
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.
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.
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.
Glassworm Poisoned 300+ GitHub Repositories With Stolen Credentials
The botnet spread through developer extensions and packages, then used stolen credentials to force-push malicious code into default branches.
ServiceNow Pre-Auth RCE Reaches Connected Proxy Server Commands
CVE-2026-6875 chained query evaluation with a sandbox escape, giving an unauthenticated attacker broad control of a ServiceNow instance and its connected proxy servers.
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.
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.