Blog

Technical analysis, threat research, reflections, and thoughts on the evolving cybersecurity landscape.

GenAI

The Evolution of Social Engineering: Weaponizing Web Lures Against Agentic AI

How cybercriminals are adapting SocGholish and ClickFix campaigns to target autonomous AI agents through Indirect Prompt Injection, agent fingerprinting, and the Parallel-Poisoned Web.

March 2026
GenAI

Building an MCP Server for Malware Traffic Analysis

How I built a natural language interface connecting Fiddler traffic capture to Gemini LLM using the Model Context Protocol.

March 2026
GenAI

Detecting AI Prompt Injection in the Wild

Building 28 EKFiddle rules and 82 UrlScan queries to detect indirect prompt injection, AI ClickFix, and credential exfiltration targeting autonomous AI agents.

March 2026
GenAI

Cognitive Induction Prompting

Reverse-engineering the 5-step LLM generation pipeline to transform prompting from guesswork into deliberate probability steering.

March 2026
Detection

From EKFiddle to YARA: Building a Detection Rule Pipeline

The workflow behind converting regex-based web traffic rules into YARA signatures for sandbox deployment.

Coming Soon
GenAI

Shadow AI on Enterprise Networks: Detection and Hunting

Writing CrowdStrike LogScale and Splunk queries to detect unauthorized LLM usage, AI coding assistants, and GenAI misuse.

Coming Soon
Threat Research

Supply Chain Attacks: Hash Auditing Across Package Repositories

Building Python tools to perform SHA256 verification across PyPI, npm, GitHub, and HuggingFace during compromise response.

Coming Soon
Reflections

Why I Still Reverse Engineer in the Age of AI

Thoughts on the enduring value of manual binary analysis and why understanding the machine still matters.

Coming Soon