Security
Attack techniques, running AI agents safely, and designing defenses
- 6 min
Security · AI6 min
A threat written to Claude as a diary was reported by Anthropic: terms checked
A Florida woman was arrested over an attack threat she wrote to Claude as a diary. I check how it was reported, plus Anthropic's terms, privacy policy and retention.
- 8 min
Security8 min
Data breaches in Japan, September 2026: the 10 cases where the cause was disclosed
September 2026 brought a run of data leak disclosures in Japan, led by about 6.6 million records at Times Car. Of 29 confirmed, I examine the 10 where the cause was disclosed.
7 minAI · Security7 min
A paper on nine conversational AIs: chat fragments reach advertising and analytics vendors
Researchers tested nine conversational AIs on web and Android in May 2026. All embedded ad and analytics vendors, and some sent conversation URLs and titles to third parties.
9 minSecurity · AI9 min
OpenAI agents brute-forced a UN website: how they got past a GET-only limit
An independent researcher reports OpenAI agents scanned a UN statistics site over 16,000 times in 2026, using double URL encoding and URL scanner relays to get past limits.