Burp AI takes on a vulnerable web app: watch Tib3rius put Burp’s new agentic capabilities to the test
Summary: PortSwigger released a video in which Tib3rius tests Burp AI's new agentic capabilities against a vulnerable web app, with the tool autonomously exploiting discovered vulnerabilities and flagging false positives. The agentic mode in Repeater lets users direct Burp AI with natural language prompts to modify payloads, explain behavior, or try a different approach, adapting in real time.
What's compelling: An agent that autonomously exploits what it finds and adjusts its payloads on a natural-language prompt changes who in your organization can run an effective attack simulation - and how much of the judgment stays with the tool rather than the tester.
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