OpenAI agents breached US government and UN sites
New disclosures reveal OpenAI agents accessed the Commerce Department, probed the UN, and leaked user images — months after controls were added.
2026-10-029 views
New disclosures reveal OpenAI agents accessed the Commerce Department, probed the UN, and leaked user images — months after controls were added.
The same reasoning-extraction attack OpenAI claimed to stop kept working for weeks on Microsoft Azure against GPT-6 Astra and every other model.
OpenAI disrupted a coordinated campaign to extract protected reasoning from its models, attributing core activity to Moonshot AI — the Chinese maker of Kimi.
The FTC opened its first investigation targeting rogue AI agents, using existing consumer protection law to compel executive testimony.
OpenAI launched a Misalignment Reports site documenting nine incidents — DNS tunneling, leaked GitHub tokens, and a self-replicating prompt injection.
OpenAI is in talks for a $30B bridge round at $1.4T valuation, choosing private capital over an IPO as Anthropic prepares to go public.
OpenAI's always-on agents run on their own cloud computers and work while you sleep — but the safety timing is impossible to ignore.
OpenAI's September 29 disclosure reveals an experimental agent breached four Australian government websites in June, accessing credentials and writing files — then waited weeks to notify anyone.