Posts

In this world of vibe-coding—where developers “fully give in to the vibes” as Andrej Karpathy put it—I’ve been exploring ways to integrate essential security thinking into this new workflow paradigm without sacrificing the speed and flexibility that makes AI-assisted coding so powerful. The Security Dilemma in Vibe-Coding Vibe-coding represents a fundamental shift in how software gets built. Instead of meticulously crafting each line, developers describe what they want and let AI generate the implementation. While this approach dramatically accelerates development, it creates blind spots around security considerations that traditional manual code reviews would catch. ...

This is Part 2 in a two-part series. Read Part 1: Bridging the Cognitive Gap Introduction LLMs don’t reason. They don’t intuit. They don’t understand risk or strategy. But they are changing how work gets done — fast. From summarizing alerts, drafting recon reports, or reverse engineering malware with tools like GhidraMCP, these agents are delivering value in surprising places. Connected Workflows: Beyond Single-Tool Interaction The most promising developments come from connecting these tools into seamless workflows. Projects like NERVEdemonstrate the power of LLM-coordinated security tools, where a natural language request triggers multiple tools in sequence without requiring manual intervention at each step. ...

Large language models (LLMs) are rapidly becoming integrated into cybersecurity workflows, with systems now able to execute reconnaissance, analyze configurations, or detect potential vulnerabilities with increasing competence. Recent models such as OpenAI’s o1 and Google’s Gemini 2.5 have introduced internal deliberation loops, longer context management, and structured reasoning prompts to expand what models can handle. But something still feels incomplete. Security expertise lives in the gray areas: when to follow a hunch, what a naming convention might imply about infrastructure design, when a redirect chain is just odd enough to be worth digging into. We try to codify these things — through system prompts, retrieval systems, or agent workflows — but what we’re really doing is projecting structure onto a system that lacks true comprehension. ...

In the rapidly evolving landscape of AI-driven cybersecurity, an interesting truth emerges: as automation capabilities increase, the value of human judgment becomes not diminished but amplified. This third installment of our series explores why the “human-in-the-loop” approach remains indispensable despite remarkable advances in AI technologies. The Fundamental Limitations of Current Agentic AI Systems The current generation of AI-driven security tools, particularly agentic systems that attempt to autonomously plan and execute tasks, face significant challenges in security contexts where precision and reliability are non-negotiable. ...

A Practical Interlude in My Cybersecurity AI Series I’m excited to share my new Censys MCP tools module that demonstrates how AI capabilities can enhance security workflows when guided by domain expertise. My previous articles here and here explored how the integration of human insight and AI will shape security’s future, introducing the hacker-strategist archetype and examining prompt engineering’s strategic dimensions. Today, I’m offering a practical example connecting those concepts through a project that brings natural language interfaces to OSINT workflows. ...

In our previous exploration of cybersecurity’s AI-driven evolution, we examined how automation is reshaping our field and giving rise to a new type of professional—the hacker-strategist. Now I want to delve deeper into perhaps the most critical skill this hybrid role demands: prompt engineering. The Strategic Dimension of Prompt Engineering Prompt engineering in cybersecurity transcends the technical mechanics of crafting effective AI queries. It represents a fundamental shift in how security expertise is applied. As routine analyses become increasingly automated, the most valuable security professionals will be those who can leverage AI capabilities effectively—knowing when to use one-shot prompts, when to build multi-step workflows, and when to deploy more complex agentic solutions—all while maintaining the creative, boundary-testing mindset that has always characterized our field. ...

After decades in cybersecurity, patterns emerge. The security landscape has always valued deeply technical experts, and this foundation remains vital. But as AI transforms our field, I’m seeing the emergence of a pivotal role at the intersection of technical depth and strategic thinking—what I call the “hacker-strategist.” This isn’t about creating a new title. Many security professionals already embody aspects of this archetype (hi!). Rather, it’s about recognizing which skills will become essential as AI reshapes cybersecurity. And, silently, those that will be obsolete. But don’t fret, there’s a way forward if you’re willing and able. ...

The security industry’s standard response to SSL/TLS protocol vulnerabilities drives organizations into urgent version upgrades, suggesting severe and immediate risk. However, the vast majority of these vulnerabilities share an major prerequisite: attackers must first achieve specific network positions. When attackers gain such positions, they typically have access to simpler and more reliable attack methods. Additionally, by analyzing technical requirements, modern mitigations, and practical attack scenarios across multiple protocol versions (SSL 3.0 through TLS 1.1), we uncover a significant disconnect between these protocol vulnerabilities, their practical risk, and how organizations seemingly over-respond. ...

This technical analysis serves as a companion piece to our main article “Is TLS Your Biggest Problem?” While the main article examines the broader implications of TLS protocol security, these appendices provide exhaustive technical details across four critical areas: network position prerequisites, browser/library implementation timelines, network position analysis, and comprehensive CVE analysis. For security practitioners and technical teams, these appendices offer the detailed technical foundation underlying the main article’s conclusions. By examining the specific technical requirements, historical implementation details, and practical attack considerations, we demonstrate why theoretical vulnerabilities often face significant practical exploitation barriers. ...

While building my own JARVIS-like assistant (yes, another one of those), I noticed something: AI output is perfectly readable as text, but throw it at a text-to-speech system and… well, let’s just say it’s not winning any audiobook awards. Here’s what I mean. Take this perfectly clear output from Claude: T h e s e r v e r a t I P 1 3 0 . 3 5 . 2 2 9 . 1 2 7 i s r u n n i n g H T T P / 4 4 3 Read that with your eyes? No problem! Crystal clear. But have your TTS system read it out loud and suddenly your technical briefing sounds like a robot having a stroke. ...