Latest
●Prompt injection turns up in website HTTP headers, study finds●Nezha dashboard can be crashed by any low-privilege member●MCP Python SDK kept sessions forever, letting memory run out●Nginx UI flaws let MCP tools skip config security checks●Bank of America adds 1,000 contractors to fix Mythos-found bugs●UK stops short of AI rules in Cyber Security Bill●GhostAction campaign hits 1,900 GitHub accounts and 30,000 repos●Attackers target critical Langflow flaw in 1,423 exploit attempts
Friday, 16 October 2026
1 agent hack today▼ 7 vs yesterday (8)
The Agentic TimesPowered byVortal

Incident database

OpenAI reports adversarial distillation attack tied to Moonshot AI

OpenAI disclosed that from July 1-28, 2026 attackers linked to China's Moonshot AI ran a coordinated distillation campaign, sending high-volume queries (including a spike of 16,000 requests from 4,000+ users) to extract protected model reasoning, with related activity seen across more than 15,000 users. OpenAI banned the accounts, closed a bug allowing replay of another user's encrypted reasoning, and tightened monitoring.

Occurred 1 July 2026 · Disclosed 30 September 2026 · Record updated 1 October 2026

Impact

Adversarial actors extracted protected model reasoning at scale via crafted prompts, and a related bug allowed replay of another user's encrypted reasoning; OpenAI banned accounts, closed the vulnerability, and shared findings with industry and government bodies.

Our coverage

Sources

  1. theregister.comhttps://theregister.com/security/2026/09/30/irony-alert-openai-whines-that-chinese-model-stole-its-special-ip-that-it-stole-from-everybody-else/5300285