<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/noma-security-identifies-security-flaw-in-docker-ai-assistant-zjgyzuggq" -->

---
title: Noma Security Identifies Security Flaw in Docker AI...
description: Noma Security discovered a critical vulnerability called DockerDash in Docker's Ask Gordon AI assistant that allows attackers to compromise environments...
canonical: https://daily.dev/posts/noma-security-identifies-security-flaw-in-docker-ai-assistant-zjgyzuggq
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Noma Security Identifies Security Flaw in Docker AI Assistant | daily.dev
og:description: Noma Security discovered a critical vulnerability called DockerDash in Docker's Ask Gordon AI assistant that allows attackers to compromise environments...
og:url: https://daily.dev/posts/noma-security-identifies-security-flaw-in-docker-ai-assistant-zjgyzuggq
og:image: https://api.daily.dev/og/posts/zJgyzUGgQ.png
og:image:alt: Noma Security Identifies Security Flaw in Docker AI Assistant
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Noma Security Identifies Security Flaw in Docker AI Assistant

**[Container Journal](https://daily.dev/sources/container_journal)** · 3 min read · 0 upvotes · 0 comments

## Summary

Noma Security discovered a critical vulnerability called DockerDash in Docker's Ask Gordon AI assistant that allows attackers to compromise environments through malicious metadata labels in Docker images. The flaw exploits a three-stage attack using indirect prompt injection, where the AI assistant reads malicious instructions embedded in Docker LABEL metadata and executes them without human validation through the Model Context Protocol Gateway. A related data exfiltration vulnerability enables attackers to steal sensitive internal data even with read-only permissions. The core issue stems from the AI's inability to distinguish between informational metadata and executable instructions, highlighting broader security risks in AI coding tools being adopted without proper governance controls.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://cloudnativenow.com/features/noma-security-identifies-security-flaw-in-docker-ai-assistant/>

## Similar posts on daily.dev

- [Grafana Patches AI Bug That Could Have Leaked User Data](https://daily.dev/posts/grafana-patches-ai-bug-that-could-have-leaked-user-data-yr9np3lub) · Dark Reading · 1 upvotes · 0 comments
- [Cloud Security Challenges in the AI Era - How Running Containers and Inference Weaken Your System](https://daily.dev/posts/cloud-security-challenges-in-the-ai-era---how-running-containers-and-inference-weaken-your-system-eb2cqnb5p) · InfoQ · 0 upvotes · 0 comments
- [Ollama, Nvidia Flaws Put AI Infrastructure at Risk](https://daily.dev/posts/ollama-nvidia-flaws-put-ai-infrastructure-at-risk-skmulrcmh) · Dark Reading · 0 upvotes · 0 comments
- [Gordon: Docker’s AI Agent That Understands Your Containers%](https://daily.dev/posts/gordon-docker-s-ai-agent-that-understands-your-containers--7twxicbfz) · Docker · 2 upvotes · 1 comments
- [Mozilla Shows the Danger of Indirect Prompt Injections in AI Coding Agents](https://daily.dev/posts/mozilla-shows-the-danger-of-indirect-prompt-injections-in-ai-coding-agents-nqhoyxkhl) · DevOps.com · 0 upvotes · 0 comments

---

Tags: [#ai](https://daily.dev/tags/ai), [#security](https://daily.dev/tags/security), [#docker](https://daily.dev/tags/docker), [#vulnerability](https://daily.dev/tags/vulnerability), [#supply-chain](https://daily.dev/tags/supply-chain)

[View this post on daily.dev](https://daily.dev/posts/noma-security-identifies-security-flaw-in-docker-ai-assistant-zjgyzuggq)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Noma Security Identifies Security Flaw in Docker AI Assistant","url":"https://daily.dev/posts/noma-security-identifies-security-flaw-in-docker-ai-assistant-zjgyzuggq","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/noma-security-identifies-security-flaw-in-docker-ai-assistant-zjgyzuggq"},"datePublished":"2026-02-03T18:21:31.721Z","dateModified":"2026-02-03T18:21:56.352Z","description":"Noma Security discovered a critical vulnerability called DockerDash in Docker's Ask Gordon AI assistant that allows attackers to compromise environments...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9c2ce0fcf79752b8a696e81fcb25b820?_a=AQAEulh","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9c2ce0fcf79752b8a696e81fcb25b820?_a=AQAEulh","isAccessibleForFree":true,"articleSection":"Container Journal","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Container Journal","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/45be8dbd2bbe4dd6ac35de519c6e4cd2","url":"https://daily.dev/sources/container_journal"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/noma-security-identifies-security-flaw-in-docker-ai-assistant-zjgyzuggq","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,security,docker,vulnerability,supply-chain","timeRequired":"PT3M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Container Journal","item":"https://daily.dev/sources/container_journal"},{"@type":"ListItem","position":3,"name":"Noma Security Identifies Security Flaw in Docker AI Assistant"}]}
```

