---
id: "CVE-2026-123653"
page: "https://infrastack.ai/live/CVE-2026-123653"
kind: "vulnerability"
aliases: ["CVE-2026-123653"]
title: "DeepSeek-Reasonix: prompt injection through document discovery lets attackers steer the model"
severity: "high"
cvss: 7.5
epss: null
exploited: false
status: "open"
category: "ai-tooling"
products: []
ecosystems: []
tags: ["ai-coding-tools", "ai-tooling", "deepseek-reasonix", "llm-prompting"]
not_affected_if: ["version-2.53.0-or-later"]
published_at: "2026-11-06T14:17:10+00:00"
first_seen_at: "2026-11-06T14:42:11+00:00"
updated_at: "2026-11-06T14:43:37+00:00"
sources: [{"source": "nvd", "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-123653", "first_seen_at": "2026-11-06T14:42:11+00:00"}]
exploit_sources: []
---

# DeepSeek-Reasonix: prompt injection through document discovery lets attackers steer the model

Link for people: https://infrastack.ai/live/CVE-2026-123653 (this .md is for agents)

DeepSeek-Reasonix, an AI coding tool, fails to neutralize input in its discoverDocs function, so crafted content can inject instructions into the LLM prompt. The sources say an attack can be started remotely and that a public exploit has been disclosed.

_Summary, check and fix written by a model from the sources; labelled as such._

## How to check

- Check the installed version of DeepSeek-Reasonix; versions up to `2.52.0` are affected.
- Look at whether the tool reads project documents through `internal/memory/doc.go` (`discoverDocs`) in your build.

## Fix

- DeepSeek-Reasonix: upgrade to `2.53.0`, per the sources.

## Timeline

- 2026-11-06T14:42:11+00:00 nvd https://nvd.nist.gov/vuln/detail/CVE-2026-123653

## Documents

- [advisory] Vendor advisory: github.com https://github.com/esengine/DeepSeek-Reasonix/security/advisories/GHSA-7v48-x992-r5w7
- [fix] Patch: github.com https://github.com/esengine/DeepSeek-Reasonix/commit/4ca33493a673c2788aa8598fbca2b2f47a69e1b8
- [fix] Release notes: github.com https://github.com/esengine/DeepSeek-Reasonix/releases/tag/v2.53.0

## From the sources

A security vulnerability has been detected in esengine DeepSeek-Reasonix up to 2.52.0. Affected is the function discoverDocs of the file internal/memory/doc.go. The manipulation leads to improper neutralization of input used for llm prompting. The attack can be initiated remotely. The exploit has been disclosed publicly and may be used. Upgrading to version 2.53.0 is able to address this issue. The identifier of the patch is 4ca33493a673c2788aa8598fbca2b2f47a69e1b8. It is suggested to upgrade the affected component.

---

_Free to read, with fair use of about 60 pages a minute. For higher limits or API access: sales@infrastack.ai_