Can Burp AI hack a website? Cyber Maddy explores the new agentic capabilities in Burp AI
Summary: CyberMaddy conducted a side-by-side experiment testing Burp AI's agentic capabilities in bug bounty hunting, documenting the exact prompts used to guide the LLM through vulnerability discovery. PortSwigger describes the results as impressive and positions the feature as on-demand AI assistance built directly into the Burp testing workflow.
Key Takeaway: The prompts that guide an LLM through vulnerability discovery are now documented and repeatable, which means the same agentic testing capability is available to defenders and attackers alike.
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