What’s new in Burp AT | Port Swigger
Summary: PortSwigger's 10 November 2026 Burp AT update lets users choose whether AI models process task data in the US or EU, a setting fixed at the project's first message that covers built-in tools but not AI calls made by scripts. Other releases add worker agents that delegate parts of an investigation, custom user-authored skills, /goal loops that run until a stated result is reached, and a 16,000 UTF-8 byte limit on goal text.
Bottom line: The processing region is locked once a project sends its first Burp AT message and cannot be changed afterward, so the choice made at project setup is the one that governs where that project's AI processing happens.
Read the original at PortSwigger Research ↗
- Topics
- Vulnerabilities & Patching
- Related
- Attackers Exploit UnrealIRCd Flaw That Enables Server-Level Command Injection Cyber Risks · Nov 14, 2026U.S. CISA adds Check Point and UnrealIRCd flaws to its Known Exploited Vulnerabilities catalog Cyber Risks · Nov 14, 2026PostgreSQL Patches 52 Flaws, Including 22-Year-Old Bug Enabling Authenticated RCE Cyber Risks · Nov 13, 2026