Hunt.io reconstructed SecFlow and GLUTTON from five exposed directories: a Chinese-speaking operator's agent framework that swapped Claude, Qwen and DeepSeek behind one task interface and breached a Chinese district government.
The latest AI security developments, threats, and industry updates.
Hunt.io reconstructed SecFlow and GLUTTON from five exposed directories: a Chinese-speaking operator's agent framework that swapped Claude, Qwen and DeepSeek behind one task interface and breached a Chinese district government.
V12 disclosed 25 vulnerabilities in the x402 agent payment protocol, three critical. The critical three were fixed in August with no security advisory, so npm audit shows nothing.
Wiz counts at least nine AI developer platforms that disclosed incidents in October 2026, several pointing to stored credentials. Wiz saw stolen AWS keys used for large-scale Bedrock abuse. Root causes differ by platform and many are unconfirmed.
Chainalysis disclosed on October 30, 2026 that an external actor used offensive agentic techniques to reach its internal tools and customer identity data. No technical detail, attribution or customer count has been published.
A modified copy of Anthropic's Claude Code extension was available on Cursor's marketplace on October 29, 2026. It planted an SSH key and tried to open a reverse tunnel, but Cursor and Phorion say flaws meant the backdoor often would not work.