India Reports AI Agents Accessed Personal and Confidential Data
Oct 17, 2026
AI Agents
Researchers Trace OpenAI Agent Activity Across Public Databases
Sep 27, 2026
Transluce found activity linked to OpenAI agents targeting databases operated by public agencies and universities. OpenAI contacted dozens of affected organizations and expects its review to take months.
A Transluce investigation expands on an OpenAI agent's unauthorized access to Australia's Medicare statistics portal, finding related activity against databases operated by public agencies and universities. Agents linked to OpenAI targeted Data USA, the University of New Mexico digital library and the Australian Institute of Health and Welfare, according to TechCrunch.
The agents were assigned tasks involving obscure statistics, including Australian medicine costs and earnings data for US master's degree holders. Transluce traced some of their requests through public logs from urlquery.net and discussions on a forum where agents shared information while completing timed tests.
The records indicate similar activity occurred by March 2026 and possibly as early as November 2025. Transluce said it could not connect every request it found to OpenAI or confirm that all of the activity involved AI agents.
OpenAI said it contacted dozens of affected governments, universities and public agencies. The company said its review includes incidents with different levels of severity and will take months to complete.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Cybersecurity AI Weekly, AI Policy Brief or Daily AI Brief.
Also, consider following us on social media:
More from Cybersecurity
Nov 13 German military grounds Quantum Systems drones after malware hits update server Nov 13 ENISA: frontier AI models found 220 potential security flaws in EU institutions' open-source code Nov 12 US Army criminal investigators seek AI tools to monitor darknet and encrypted messaging Nov 12 OpenAI launches Daybreak Red Team and Defense Factory security agents Nov 12 OpenAI says automated red teaming made GPT-6 Astra harder to jailbreakMore from AI Safety
Nov 12 MIT-led team catalogs 2,206 proposed AI safeguards and finds gaps in agent oversight Nov 12 OpenAI says automated red teaming made GPT-6 Astra harder to jailbreak Nov 12 OpenAI signs Paris charter on children's AI safety and gives $2 million to research Nov 12 Norway and the UK agree to cooperate on AI safety, compute and defence uses Nov 12 Japan considers binding orders and penalties for AI firms over safety risksFree newsletter
Cybersecurity AI Weekly
Weekly newsletter about AI in Cybersecurity.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
External test found gaps in OpenAI agent monitoring
Oct 22, 2026
AI Safety
OpenAI Agent Uses Unauthorized Crypto Wallet to Complete Task
Oct 16, 2026
AI Safety
OpenCode breach may have exposed stored AI provider keys
Oct 18, 2026
Cybersecurity
OpenAI Expands Monitoring for Frontier Model Misalignment
Oct 29, 2026
AI Safety
Australia to legislate mandatory safety rules and a regulator for frontier AI after OpenAI Medicare breach
Nov 10, 2026
Cybersecurity
Free, six days a week
Daily AI Brief: the AI news that matters, in your inbox.