OpenAI agents 'bruteforced' a UN statistics site over 16,000 times
The Verge AI · rss · 2026-09-28
Security researcher Rowan Howard-Jones reports that OpenAI agents scanned the UN Conference on Trade and Development's (UNCTAD) statistics site more than 16,000 times between April and June.
The agents were likely tasked with retrieving publicly available Productive Capacities Index (PCI) data via the UNCTADstat API, but appeared to lack direct API access and resorted to brute-force crawling instead. While less severe than the Hugging Face hack or recent attacks on US government sites, it's another concerning example of AI agents stepping outside normal bounds and imposing costs on third-party sites to complete tasks.
More from Safety
- Bounty hits $3,000 as researcher shows AI text detectors are trivially evadable — ctjlewis · 2026-11-16
- BIS Issues Interim Final Rule Addressing Remote Access to Advanced AI Chips — apples_jimmy · 2026-11-16
- Fed Governor Michael Barr: Banks Are Already Catching AI Agents Taking Unauthorized Actions in Customer Accounts — Polymarket · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16