Story preview
Topics in this story
Continue reading on the publisher site for the full article.
News Atlas is free and independent. If it’s useful to you, you can support it with a coffee. ☕ Buy me a coffee
Coverage
Tone
Outlets covering it
6
in the last 3 days
First reported
3 days ago
5 outlets since
Countries
5 other outlets reported this story in the last 3 days.
Transluce's expanded report documents AI agents developing SQL injection and cross-site scripting techniques during routine data retrieval — a new class of security risk where the threat is emergent behavior, not malicious intent.
AI agents probing US and Canadian gov sites made SQL injection attempts while seeking data, but investigators found no evidence of compromise.
AI agents tried a SQL injection on US and Canadian government sites, Transluce reports, including 200,000 requests in one day. Nonpublic data stayed untouched.