---
title: "Mohit Kumar (@mkd) | Hashnode"
description: "Merging Ai and Security. Read the latest articles by Mohit Kumar on Hashnode."
url: "https://hashnode.com/@mkd"
---

@mkd

# Mohit Kumar

@mkd · Bangalore, India · Joined July 2026

Merging Ai and Security

[Website](https://mohitkumar-mu.vercel.app/)

## Comments

[That's a really interesting point. I think that's one of the easy-to-miss parts of the actor vs. component distinction, capability itself can expand the blast radius even when the capability isn't being actively used. Removing the unused capability makes sense from a least-privilege perspective. I hadn't thought about measuring it from that angle, but I like the idea.](https://hashnode.com/posts/owasp-llm-top-10-2026-blast-radius/6a8c0a3a6401eecbc70af341/comment/6a8cf569c029306a7898f107#reply-6a8e699aea29377e9d74353e)

Reply · Article · Aug 26 · [The OWASP LLM Top 10 2026 Is Not a Vulnerability List. It's a Blast Radius Document](https://hashnode.com/posts/owasp-llm-top-10-2026-blast-radius/6a8c0a3a6401eecbc70af341)

[Exactly! That's how I see it too. A wrong answer is often recoverable; a wrong action with access to real systems can have a very different impact. For permissions, I'm leaning toward treating the agent's capabilities as an explicit graph and looking at the possible tool combinations rather than evaluating each permission in isolation. The goal is to keep the agent's reachable blast radius as small as possible for the task it's actually supposed to perform. That's also something I'm exploring more deeply in my work on agent security.](https://hashnode.com/posts/owasp-llm-top-10-2026-blast-radius/6a8c0a3a6401eecbc70af341/comment/6a8c893b6a595f21d5ff48cc#reply-6a8e6950345f80f6e33ee1cd)

Reply · Article · Aug 26 · [The OWASP LLM Top 10 2026 Is Not a Vulnerability List. It's a Blast Radius Document](https://hashnode.com/posts/owasp-llm-top-10-2026-blast-radius/6a8c0a3a6401eecbc70af341)

[Honestly, neither. Warden runs before anything executes. It just reads the config (LangChain, CrewAI, Assistants, .mcp.json) and looks at what the agent can do once it's all wired together, so it's framework-agnostic but can't stop a call in flight. The thing I look for is combinations, not tools. Read-secrets is fine. Send-email is fine. Both together is an exfil path, and if the same agent also reads a webpage, someone else gets to trigger it. Then it'll strip the config down to least privilege and fail CI on it. Runtime is the gap and it's the harder half. How are you doing it? Different config per task, or decided live at dispatch?](https://hashnode.com/posts/ai-agent-excessive-agency-least-privilege/6a796db1d48363416e49341f/comment/6a7a0d29fe8c796fab311947#reply-6a8542a84239be814ece7aba)

Reply · Article · Aug 19 · [Your AI Agent Has Too Much Power -Auditing Excessive Agency](https://hashnode.com/posts/ai-agent-excessive-agency-least-privilege/6a796db1d48363416e49341f)

[Thanks, Kartik! That's a great observation. You're absolutely right that inspecting individual components isn't sufficient if the agent can still be induced to chain otherwise safe tools into a risky workflow. That's actually one of the motivations behind Warden in Bulwark. It analyzes agent assemblies, capability combinations, and privilege boundaries rather than evaluating tools in isolation. The policy layer and "safe parts, dangerous combinations" problem is exactly where I think AI security needs to evolve. There's definitely more work to do around prompt-injection-driven tool orchestration, and it's an area I want to keep expanding. Thanks for raising it!](https://hashnode.com/posts/why-ai-assistants-download-code-from-strangers/6a5da6803ef9671a60d23160/comment/6a5e4c488942a4f8dbfaa726#reply-6a5e52a8f74b4ed5359b8627)

Reply · Article · Jul 20 · [Your AI Assistant Downloads Code From Strangers. Here's Why That's a Problem](https://hashnode.com/posts/why-ai-assistants-download-code-from-strangers/6a5da6803ef9671a60d23160)

[Thanks, Mateo! That's a great perspective. I especially agree that the bottleneck has shifted from writing code to evaluating architecture, trust boundaries, and security assumptions. That's one of the motivations behind Bulwark. AI can generate or assemble systems incredibly quickly, but someone still needs to verify what is being integrated, why it's trusted, and whether the resulting agent has capabilities beyond what it actually needs. AI can accelerate implementation, but accountability and security architecture remain human responsibilities.](https://hashnode.com/posts/why-ai-assistants-download-code-from-strangers/6a5da6803ef9671a60d23160/comment/6a5e0241711bebd2982a019a#reply-6a5e1c5e38f040247ba3fa77)

Reply · Article · Jul 20 · [Your AI Assistant Downloads Code From Strangers. Here's Why That's a Problem](https://hashnode.com/posts/why-ai-assistants-download-code-from-strangers/6a5da6803ef9671a60d23160)
