Announcing MCP Toolbox Java SDK v1.0: Agentic data access for the enterprise
cloud.google.com·6d ago
Cloud & Infrastructure
The New Stack·Jul 29·5 min read
“The beast needs a cage”: Why PortSwigger’s agentic pentesting is kept safe behind bars
TL;DR
PortSwigger has launched Burp AT, a new agentic AI tool for professional pentesting within its Burp Suite platform, allowing pentesters to define tasks while maintaining control over scope and permissions. This innovation aims to enhance the effectiveness of vulnerability testing in web security.
✦ Why It Matters
Consider integrating Burp AT into your pentesting workflow to enhance vulnerability detection and management.
Key Takeaways
- Explore Burp AT for integrating AI into your pentesting efforts.
- Maintain human oversight to ensure security and accountability.
- Utilize structured methodologies for repeatable testing processes.
- Start with tight controls before increasing AI autonomy in testing.
How It Works
Burp AT allows pentesters to assign tasks to AI agents while enforcing strict controls on actions through a deterministic layer. This ensures that all requests are vetted for scope and permissions, maintaining a clear audit trail of activities.