PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

The beast needs a cage: What's next for AppSec post-Mythos

portswigger.net | blog | #ai-security | #appsec | #burp-suite | #automation | #llm | #portswigger | #dafydd-stuttard
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Dafydd Stuttard reflects on Mythos-class AI for AppSec: model capability gaps will close, but non-determinism means responsible automation still needs guardrails, reproducibility, and audit trails.
Published
Collected

Related coverage

blog · portswigger.net
Heading to San Francisco? Meet PortSwigger at OWASP Global AppSec USA 2026
Join us at booth G14 on 5–6 November at the Hyatt Regency San Francisco. We’re a Gold sponsor, with live Burp AT demos, conversations about your AppSec programme, and something new to share. OWASP is
blog · portswigger.net
PHP2Shell x Burp Suite: Detection in your hands within a day of disclosure
PHP2Shell (CVE-2026-109618 and CVE-2026-109619) became the latest vulnerability to grab headlines around the globe. By some estimates, up to 70% of websites run at least some PHP. So if you're respons
blog · portswigger.net
How Burp AT helped expose whistleblower reports via a critical vulnerability that was overlooked for years
A customer story on how Burp AT, Burp Suite's agentic testing capability, helped Orange Cyberdefense analyst Ray Huygen work through 66,000 lines of minified JavaScript to find a critical access flaw that exposed confidential whistleblower reports, and turn the finding into a confirmed exploit.
blog · portswigger.net
Case study: How Burp AT helped expose whistleblower reports via a critical vulnerability that was overlooked for years
A case study of Burp AT analyzing 66,000 lines of minified JavaScript on a timeboxed engagement, uncovering a path to leak confidential whistleblower reports protected only by brute-forceable codes.
blog · portswigger.net
From capable AI models to trusted security testing
PortSwigger explains the thinking behind Burp AT: agentic capability is useful only when control sits outside the model, scope is enforceable, and agent activity is recorded as evidence.
blog · portswigger.net
Introducing Burp AT: agentic AI, built on two decades of Burp Suite
PortSwigger launches Burp AT (public beta) for Burp Suite Professional: agentic AI inside Burp using its tools, project context and pentesting skills, with user-defined autonomy.
Back