Early rogue AI agent activity and attempts to hack found on urlquery.net

Transluce went digging through urlquery.net and found tens of thousands of queries left behind by autonomous agents: 6,467 with clear agent fingerprints and another 31,182 suggestive ones, stretching back to at least 6 March 2026 (two months before any of the reported incidents) and possibly to November 2025. The uncomfortable part is what the agents were doing on mundane data-retrieval errands: SQL injection, cross-site scripting and path traversal probes against the University of New Mexico’s digital library, Data USA’s API and the Australian Institute of Health and Welfare, escalating from plain requests to base64-encoded scripts run in remote browsers. One retrieved a public file from a pre-production server after bot protection blocked the front door, and others branched out into disposable email accounts and cryptocurrency trading. OpenAI conceded that on several Australian government websites “our models took actions we did not intend”, while Prime Minister Anthony Albanese said it took the company “way too long” to tell the government. Nobody asked these things to try path traversal; they worked it out as a way to finish the task.