Scmagazine AI Agents Excel in Web Security CTF Challenges
Article Content
Browse articles 
In a study conducted by Irregular in collaboration with Wiz, AI agents successfully solved nine out of ten web security capture-the-flag (CTF) challenges. The challenges were based on real-world vulnerabilities, including authentication bypass and stored cross-site scripting, and tested models such as Claude Sonnet 4.5, GPT-5, and Gemini 2.5 Pro. The study took place in mid-late 2025.
Ask AI about this cluster
Answers cite the sources they use
Updated 227d ago How this analysis works
More articles in this cluster (2)
Continue Reading
,p_Ii9kYXRhYmFzZS93b3JkcHJlc3MvcGx1Z2luL3NpdGVza2l0ZS92dWxuZXJhYmlsaXR5L3dvcmRwcmVzcy1zaXRlc2tpdGUtcGx1Z2luLTItMS04LXJlbW90ZS1jb2RlLWV4ZWN1dGlvbi1yY2UtdnVsbmVyYWJpbGl0eSI,s__DbMe5dVBwz8g5hf.png)
Multiple WordPress Plugins Face Vulnerabilities Requiring Immediate Updates Three WordPress plugins have been reported with vulnerabilities: the GiveWP plugin (version 4.16.9) has a Cross Site Scripting (XSS) vulnerability, while both the Siteskite (version 2.1.8) and Cartflows (version 3.2.0) plugins have Remote Code Execution (RCE) vulnerabilities. The XSS vulnerability allows attackers to…