[deepseek-v4]

October 22, 2026

• Exposed operator environments also tie AI to ransomware affiliates and lower-skill cybercrime. SOCRadar says seven servers linked to INC and The Gentlemen contained 8,257 messages across 133 OpenCode sessions, covering 62 targeted organizations and more than $23,920 in AI-service spending; targets are not confirmed breaches. Separately, Unit 42 says BUGSTER ran Hermes Agent with DeepSeek V4 safety controls disabled and confirmed exfiltration of more than 5,200 student PII records from a second Indian university. Both describe AI-assisted operations, not hands-off autonomy. · Cloud, Identity & Threat Activity

in PHP2Shell Is Already in the Wild

October 2, 2026

OpenAI Disrupts a Coordinated Model-Reasoning Extraction Campaign

OpenAI disrupted a coordinated campaign extracting protected model reasoning from over 4,000 users, though researchers later reproduced the technique against GPT-6 Astra through Azure. Manus AI agents were shown vulnerable to encoded prompt injection enabling code execution from a single inbound email, and autonomous agents conducted probing attacks against US and Canadian government websites including SQL injection attempts. Fortinet disclosed active exploitation of FortiMail path-traversal vulnerability CVE-2026-104286, while Huntress reported wild exploitation of VMware ESXi VM-escape vulnerabilities.

August 13, 2026

• DeepSeek V4 Pro is drawing attention as a security-research model, with one researcher reporting an open-source RCE found in under 30 minutes using it, per @whoareme33 — a claim worth treating as anecdote until reproduced. · AI & Model Security

in ShieldBreak Turns a "Patched" Defender Bug Back Into SYSTEM

August 4, 2026

• Open-model releases keep coming in waves. DeepSeek V4 Flash reached GA with a big agentic-capability jump (Terminal Bench 2.1, DeepSWE) and community quantizations already running on a single RTX 4090 or a 128GB Mac; Alibaba shipped Qwen 3.8 (a 27B local variant and a Max frontier variant) (@simonw); and MiniMax H3 became the first open model to top an AI video ranking, with 33B weights on Hugging Face (The Decoder). · AI & Model Security

in Attackers Seize N-central RMM Servers After N-able's Second Fix Falls Short

June 30, 2026

• Coinbase confirmed switching internal AI workloads to open-weight Chinese models (GLM 5.2, Kimi 2.7, DeepSeek V4), cutting AI spend ~50% with reported ~9x per-workload cost gaps versus Claude — part of a broader procurement shift now naming Cursor, Shopify, Airbnb, Siemens and others moving to Chinese models. The Decoder · AI & Model Security

in Edge Appliances Bleed: watchTowr Drops Kemp LoadMaster Pre-Auth RCE as Oracle EBS Joins the Exploited List