---
title: "Discussion on \"The OWASP LLM Top 10 2026 Is Not a Vulnerability List. It's a Blast Radius Document\" | Hashnode"
description: "Discussion on \"The OWASP LLM Top 10 2026 Is Not a Vulnerability List. It's a Blast Radius Document\". What changed, what moved, and how to turn ten risks into ten controls"
url: "https://hashnode.com/posts/owasp-llm-top-10-2026-blast-radius/6a8c0a3a6401eecbc70af341"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [The OWASP LLM Top 10 2026 Is Not a Vulnerability List. It's a Blast Radius Document](https://mohitkumar1.hashnode.dev/owasp-llm-top-10-2026-blast-radius?utm_source=hashnode&utm_medium=feed)

What changed, what moved, and how to turn ten risks into ten controls

Aug 24 · 7 min read · mohitkumar1.hashnode.dev  
Read the article

-   [#ai-security](https://hashnode.com/tag/ai-security)
-   [#ai](https://hashnode.com/tag/ai)
-   [#ai-agents](https://hashnode.com/tag/ai-agents)
-   [#llm](https://hashnode.com/tag/llm)
-   [#owasp](https://hashnode.com/tag/owasp)
-   [#cybersecurity](https://hashnode.com/tag/cybersecurity)

## Written by

[Mohit Kumar](https://hashnode.com/@mkd)

@mkd · Bangalore, India

  
[View profile](https://hashnode.com/@mkd)

Merging Ai and Security

Cybersecurity Engineer building secure AI systems, agentic applications, and developer tools. Passionate about AI security, cloud, and turning research into production-ready software. Sharing projects, technical deep dives, and lessons learned along the way.

## Responses 4

Markdown supported · ⌘↵ to post

[Andrew](https://hashnode.com/@rizzdev)

[Aug 25](https://hashnode.com/posts/owasp-llm-top-10-2026-blast-radius/6a8c0a3a6401eecbc70af341/comment/6a8cf569c029306a7898f107)

A code graph tool measured net-negative on a small repo, so I removed it. That unused capability still made it an actor.

[Mohit Kumar](https://hashnode.com/@mkd)

[Aug 26](https://hashnode.com/posts/owasp-llm-top-10-2026-blast-radius/6a8c0a3a6401eecbc70af341/comment/6a8cf569c029306a7898f107#reply-6a8e699aea29377e9d74353e)

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.

[Kartik N V J K](https://hashnode.com/@kartik-nvj)

[Aug 24](https://hashnode.com/posts/owasp-llm-top-10-2026-blast-radius/6a8c0a3a6401eecbc70af341/comment/6a8c893b6a595f21d5ff48cc)

Excessive Agency climbing to number three matches what I'm seeing, the risk moved from what the model says to what it's allowed to do. Blast radius is the right lens, a wrong answer is cheap but a wrong action with tool access is not. How are you scoping agent permissions to keep that radius small?

[Mohit Kumar](https://hashnode.com/@mkd)

[Aug 26](https://hashnode.com/posts/owasp-llm-top-10-2026-blast-radius/6a8c0a3a6401eecbc70af341/comment/6a8c893b6a595f21d5ff48cc#reply-6a8e6950345f80f6e33ee1cd)

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.
