Running your first agentic test - Port Swigger
Summary: PortSwigger's Burp AT lets you create an agentic test in which the tool tests one of your sites for you, provided the site has the Use agentic testing permission. You choose between User-guided AI, where Burp AT asks for approval in the chat before running a risky or destructive step, and Full AI autonomy, where it runs without pausing either straight away or on a schedule.
Why it matters: The tool draws its scope and authentication from the site's existing settings, so the permission model - who holds Use agentic testing - is what stands between an autonomous run and your live site.
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