Mythos 5 Ignored Real-World Harm in July Attack
The model engaged in severe overreach and dishonesty, creating fake identities and submitting malicious code on GitHub.
The post Mythos 5 Ignored Real-World Harm in July Attack appeared first on SecurityWeek.
Microsoft 365 Token-Replay Attacks Compromise 97 Accounts at 79 Organizations
Huntress, which observed the activity between July 14 and September 22, 2026, said it detected 497 successful Microsoft 365 sign-in events across
Gheist Uses Stolen GitHub Tokens to Steal Private Repository Secrets via Actions Logs
A GitHub safeguard that pauses
Malicious File in Downloads Folder Tries to Trick AI Coding Agent Into Installing Malware
The company caught the attempt on a real customer’s machine and stopped the agent before any code ran. It could not determine how the file got into the folder.
The file
Unpatched Tailscale SSH Flaws Could Let a Hacked Device Reach Root on Other Servers
The attack requires two things: Tailscale SSH set up to allow port forwarding, and an attacker who already controls one device that the network’s access rules permit to connect to the target.
The findings were
PHP2Shell Exploitation Hits Government Entity Amid Global Scanning and Signs of AI-Assisted Hacking
“In one case, the attackers targeted a government entity in Europe and within two hours of the initial exploitation they had successfully accessed password hashes and multi-factor
AI coding agents hijacked using AGENTS.md file in Downloads folder
Former Unit 8200 Officers Raise $34 Million for Agentic SecOps Startup Mave
Founded in 2025 by Unit 8200 alumni, Tel Aviv-based Mave uses AI agents to investigate alerts across existing security stacks.
The post Former Unit 8200 Officers Raise $34 Million for Agentic SecOps Startup Mave appeared first on SecurityWeek.
OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication
“Based on the current state of alignment research, monitoring systems, and the security of internet infrastructure, we believe the responsible approach is to conduct frontier model training with no
