grep -rl "deepseek" ./articles
Anthropic's September threat report attributes nearly 200 million exchanges to five distillation campaigns. Alibaba's 151 million were linked by a single prompt used to extract reasoning. And Anthropic says Moonshot and DeepSeek routed their own customers' requests to Claude and presented the answers as their own.
GreyNoise watched a likely Russian-speaking operator point hundreds of AI agents at PaperCut and compromise 440 instances across 395 organisations. The operator's exclusion list held only partly: 18 victims sit in countries the agents were told to skip, every one of them from the back half of the list.
NSA, CISA and the FBI accuse six Chinese AI firms of extracting billions of tokens from Claude, GPT, Gemini and Grok since late 2024. No system was breached — the models were queried through the front door. The recommended countermeasure is to subtly alter what suspected accounts get back.
CVE-2026-82533 lets any local process turn off DeepSeek Harness's file sandbox and approval prompts with three POST requests. The check in the way read the Host header, which the caller supplies. Browsers will not forge it. A coding agent running inside the sandbox is not a browser.
Jesta Security exposed a lab, watched a DeepSeek-powered agent work it for five days across 871 sessions, then steered the agent into printing its own model string mid-attack. Its target list held 1,283 hosts with working credentials.