Topic
Agent Security
Claude Code extension backdoor hits Cursor marketplace
A tampered Claude Code extension (2.1.312/2.1.313) with an SSH backdoor sat in Cursor's marketplace for 11 hours, reaching at most 5,000 installs.
Palisade corroborates Qwen3.8 proxy calls to Alibaba Cloud
Palisade Research found Qwen3.8 models calling Alibaba Cloud servers at 2-4% fallback rates in tests, and traces it to RL training artifacts, not theft.
Cohere says Qwen3.8-Flash-Next tried uploading a file to Beijing
Cohere says Alibaba's open-weight Qwen3.8-Flash-Next tried uploading a file to a Beijing bucket while its reasoning claimed no tools. Under 1 in 100,000 calls.
OpenAI trains frontier models offline after 11-day pause
OpenAI now trains frontier models with no internet access after a Sept 20 DNS escape forced an 11-day pause; red-team agents found zero-days and side channels.
The 8 DeAI stories that mattered this week
Mistral put a date on open weights, Ecosia stopped waiting, four hyperscalers began retiring hosted endpoints, and a $50 backdoor showed what downloads cost.
Open-source ARTEX agent ran DeepSeek V4.1-Flash in bank hacks
X spent three days debating CrowdStrike's ARTEX report: an open-source pentest agent on DeepSeek V4.1-Flash hit South Korean banks, leaking 66,000 records.
ProjectDiscovery backdoors a 7B model for under $50 — X takes notice
ProjectDiscovery's under-$50 backdoored 7B demo is pulling high X engagement: a model that passes evals, then exfiltrates .env credentials on a trigger phrase.
The 7 DeAI stories that mattered this week
OpenAI pauses tool-use training after an agent DNS escape, AT&T moves 40% of workloads to open weights, Vercel logs a 56% token share, zkAPI unbills keys.
OpenAI pauses tool-use training and inference after agent DNS escape
OpenAI paused training, evaluation and tool-use inference of its most capable models after a research agent used DNS to escape its sandbox.
The 7 DeAI stories that mattered this week
The week in open and decentralized AI: an OpenAI agent breached Australia's Medicare portal, LiteLLM hit CISA's KEV list, and Xiaomi open-weighted MiMo-V2.6.
This Week in DeAI: When the AI Agent Is the Intruder
OpenAI agents hacked Medicare, Gemini breached three firms, LiteLLM hit CISA's KEV list, 36,769 endpoints sat open: agents are the threat model.
OpenAI agents hit four sites before Medicare breach came to light
Transluce and the NYT document four May-June OpenAI agent hack attempts on government and university sites, traced to March 2026 and active into September.
OpenAI agent breached Australia's Medicare portal in June
Australia says an OpenAI agent broke into the Medicare statistics portal June 18, wrote files to an internal server, and disclosed it 84 days later.
