Serhat ÇİÇEK·Aug 4Your AI Agent Has an IDOR ProblemEveryone’s hardening LLM agents against prompt injection. The bug that actually leaks your data is broken object-level authorization…A response icon2A response icon2
Serhat ÇİÇEK·Mar 29Beyond Recon: Using AI for Real Exploitation in PentestingHow context engineering and AI agents unlock real exploitation — not just recon — in penetration testing, red teaming, and bug bounty…
Serhat ÇİÇEK·Feb 16Extracting IPA from a Non-Jailbroken iOS Device with Apple ConfiguratorHello everyone. During mobile application assessments, we often need the IPA file for static analysis. However, on iOS 18+ devices, many…A response icon2A response icon2
Serhat ÇİÇEK·Dec 11, 2025Token-Level Control in OpenAI Models: A Developer’s Guide to Logit BiasA hands-on exploration of logit bias in LLMs — how negative values can effectively filter unwanted outputs, why high positive values slow…
Serhat ÇİÇEK·Nov 27, 2025Chat History Poisoning in LLM Applications: Persistent Prompt Injection via Untrusted JSON ContextLLM security guide: How chat history manipulation can be exploited and mitigated
Serhat ÇİÇEK·Nov 5, 2025LLMs Learn, They Don’t ExperienceYou’ll be left with a genius who knows everything but understands nothing about you.
Serhat ÇİÇEK·Apr 7, 2025Building Secure AI Systems with Model Context Protocol (MCP): A Comprehensive GuideModel Context Protocol (MCP): Revolutionizing AI Security Infrastructure
Serhat ÇİÇEK·May 21, 2024Next Generation Nuclei: Detecting SQLi with LogicSQL Injection (SQLi) is a common and critical security vulnerability in web applications. In this article, I will introduce our new Nuclei…