MediumCVE-2026-123653

    esengine DeepSeek-Reasonix doc.go discoverDocs llm prompting input (CVE-2026-123653)

    Published Last modified Sources: CVE.org

    Share

    What is affected, what to do

    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.

    An exploit is publicly available. The available sources name no fixed version. Check the vendor guidance in the references below.

    Affected
    • Esengine DeepSeek-Reasonix eq 2.0..2.0
    • Esengine DeepSeek-Reasonix eq 2.1..2.1
    • Esengine DeepSeek-Reasonix eq 2.2..2.2
    • Esengine DeepSeek-Reasonix eq 2.3..2.3
    • Esengine DeepSeek-Reasonix eq 2.4..2.4
    • Esengine DeepSeek-Reasonix eq 2.5..2.5
    • Esengine DeepSeek-Reasonix eq 2.6..2.6
    • Esengine DeepSeek-Reasonix eq 2.7..2.7
    • Esengine DeepSeek-Reasonix eq 2.8..2.8
    • Esengine DeepSeek-Reasonix eq 2.9..2.9
    • Esengine DeepSeek-Reasonix eq 2.10..2.10
    • Esengine DeepSeek-Reasonix eq 2.11..2.11
    • Esengine DeepSeek-Reasonix eq 2.12..2.12
    • Esengine DeepSeek-Reasonix eq 2.13..2.13
    • Esengine DeepSeek-Reasonix eq 2.14..2.14
    • Esengine DeepSeek-Reasonix eq 2.15..2.15
    • Esengine DeepSeek-Reasonix eq 2.16..2.16
    • Esengine DeepSeek-Reasonix eq 2.17..2.17
    • Esengine DeepSeek-Reasonix eq 2.18..2.18
    • Esengine DeepSeek-Reasonix eq 2.19..2.19
    • Esengine DeepSeek-Reasonix eq 2.20..2.20
    • Esengine DeepSeek-Reasonix eq 2.21..2.21
    • Esengine DeepSeek-Reasonix eq 2.22..2.22
    • Esengine DeepSeek-Reasonix eq 2.23..2.23
    • Esengine DeepSeek-Reasonix eq 2.24..2.24
    • Esengine DeepSeek-Reasonix eq 2.25..2.25
    • Esengine DeepSeek-Reasonix eq 2.26..2.26
    • Esengine DeepSeek-Reasonix eq 2.27..2.27
    • Esengine DeepSeek-Reasonix eq 2.28..2.28
    • Esengine DeepSeek-Reasonix eq 2.29..2.29
    • Esengine DeepSeek-Reasonix eq 2.30..2.30
    • Esengine DeepSeek-Reasonix eq 2.31..2.31
    • Esengine DeepSeek-Reasonix eq 2.32..2.32
    • Esengine DeepSeek-Reasonix eq 2.33..2.33
    • Esengine DeepSeek-Reasonix eq 2.34..2.34
    • Esengine DeepSeek-Reasonix eq 2.35..2.35
    • Esengine DeepSeek-Reasonix eq 2.36..2.36
    • Esengine DeepSeek-Reasonix eq 2.37..2.37
    • Esengine DeepSeek-Reasonix eq 2.38..2.38
    • Esengine DeepSeek-Reasonix eq 2.39..2.39
    • Esengine DeepSeek-Reasonix eq 2.40..2.40
    • Esengine DeepSeek-Reasonix eq 2.41..2.41
    • Esengine DeepSeek-Reasonix eq 2.42..2.42
    • Esengine DeepSeek-Reasonix eq 2.43..2.43
    • Esengine DeepSeek-Reasonix eq 2.44..2.44
    • Esengine DeepSeek-Reasonix eq 2.45..2.45
    • Esengine DeepSeek-Reasonix eq 2.46..2.46
    • Esengine DeepSeek-Reasonix eq 2.47..2.47
    • Esengine DeepSeek-Reasonix eq 2.48..2.48
    • Esengine DeepSeek-Reasonix eq 2.49..2.49
    • Esengine DeepSeek-Reasonix eq 2.50..2.50
    • Esengine DeepSeek-Reasonix eq 2.51..2.51
    • Esengine DeepSeek-Reasonix eq 2.52.0..2.52.0

    Not sure whether and how you are affected? Ask a question about this vulnerability

    Metrics

    6.3

    Priority

    XIEM Effective CVSS: highest available CVSS rating from NVD and vendor data.

    Source: NVD, CVSS v3

    6.3

    CVSS v3

    Severity Medium on the scale from 0 to 10.

    Source: CVE.org

    —

    EPSS score

    No value is available for this vulnerability.

    Show all metrics
    Severity
    Medium
    Priority (0–325)

    The priority score is a consolidated metric that condenses several individual signals into a single, action-guiding ranking: technical severity (CVSS), exploitation likelihood (EPSS), known-exploited status (KEV) and the context of the affected asset. The aim is to answer the only truly important question in vulnerability management: what first?

    Read in glossary
    61.50 Methodology
    Exploit maturity

    An exploit is code or a technique that specifically uses a concrete vulnerability to force unintended behaviour — such as executing code or escalating privileges. It is the tool that turns a theoretical flaw into a practical attack.

    Read in glossary
    PoC (publicly reported)
    XIEM Effective CVSS

    XIEM® is the tiered managed-security operating model from NEOSEC and a registered trademark of NEOSEC GmbH. It extends classic SIEM — the central collection, normalisation and correlation of security-relevant events — with endpoint forensics, network visibility and deception technology, and consolidates them into three building tiers: Sentry, Orchestrate and Command.

    Read in glossary
    6.3 Methodology
    CVSS v3

    CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions.

    Read in glossary
    6.3
    CVSS v4

    CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions.

    Read in glossary
    5.3
    KEV status

    The KEV catalogue is a list maintained by the US authority CISA of vulnerabilities for which active exploitation in the wild has been confirmed. It answers not the question „how severe?“ but „is it already being attacked?“ — thereby sharply prioritising patching.

    Read in glossary
    —
    Published
    CWE

    CWE is a catalogue of typical weakness types in software and hardware — such as flawed input validation, unsafe memory handling or poor authentication. Where a CVE names a concrete vulnerability in a concrete product, a CWE describes the underlying class of defect.

    Read in glossary
    CWE-1427, CWE-349

    Detection rules

    No NEOSEC detection rule is available for this vulnerability yet.

    Classification under NIS2 and CRA

    Rule-based classification from exploitation status and severity. It does not replace a case-by-case assessment.

    NIS2

    NIS2 is EU Directive (EU) 2022/2555 to raise the level of cybersecurity across the Union. It substantially broadens obligations compared with the first NIS directive: more sectors, mandatory risk management, staged reporting duties and personal accountability of senior management.

    Read in glossary
    Handle the vulnerability in regular vulnerability handling under Art. 21(2)(e) NIS2.
    CRA

    The CRA is EU Regulation (EU) 2024/2847 setting horizontal cybersecurity requirements for „products with digital elements“ — from industrial controllers and software to connected consumer devices. For the first time manufacturers must ensure security across the entire product lifecycle, handle vulnerabilities and provide security updates.

    Read in glossary
    From 11.12.2027, Annex I Part II CRA requires manufacturers of affected products with digital elements to handle vulnerabilities without delay and provide security updates.
    ISO/IEC 27001

    ISO/IEC 27001 is the internationally leading standard for an information security management system (ISMS). It describes a risk-based, process-oriented framework to systematically plan, implement, review and improve information security.

    Read in glossary
    Control A.8.8, management of technical vulnerabilities: assess relevance to your systems, plan remediation and keep evidence.

    Description

    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.

    Source: cvelistv5, NVD (NIST)

    Affected products

    The following versions are affected. Older releases of the same product line are also vulnerable unless stated otherwise.

    Affected products
    Affected versionsFixed in
    esengineDeepSeek-Reasonix
    • 2.49
    • 2.21
    • 2.20
    • 2.26
    • 2.14
    • 2.22
    • 2.24
    • 2.5
    • 2.18
    • 2.29
    • 2.51
    • 2.19
    • 2.48
    • 2.27
    • 2.28
    • 2.25
    • 2.50
    • 2.3
    • 2.36
    • 2.30
    • 2.2
    • 2.52.0
    • 2.39
    • 2.37
    • 2.31
    • 2.32
    • 2.43
    • 2.46
    • 2.23
    • 2.45
    • 2.41
    • 2.13
    • 2.7
    • 2.16
    • 2.15
    • 2.33
    • 2.35
    • 2.47
    • 2.38
    • 2.34
    • 2.42
    • 2.1
    • 2.11
    • 2.17
    • 2.4
    • 2.44
    • 2.8
    • 2.10
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —

    Weakness classes (CWE)

    • CWE-1427Improper Neutralization of Input Used for LLM Prompting

      Base

      The product uses externally-provided data to build prompts provided to large language models (LLMs), but the way these prompts are constructed causes the LLM to fail to distinguish between user-supplied inputs and developer provided system directives.

      Entry at MITRE CWE-1427

    • CWE-349Acceptance of Extraneous Untrusted Data With Trusted Data

      Base

      The product, when processing trusted data, accepts any untrusted data that is also included with the trusted data, treating the untrusted data as if it were trusted.

      Entry at MITRE CWE-349

    Public exploit references

    Publicly reported proof-of-concepts, exploit modules and detection templates for this vulnerability. NEOSEC links to the original sources only and does not provide any exploit code.

    Public exploit references
    Reference tagged as exploitgithub.com (opens in a new tab)PoC (publicly reported)reported, not verified—

    References & sources

    • github.comesengine/DeepSeek-ReasonixProduct
    • github.comesengine/DeepSeek-Reasonix/commit/4ca33493a673c2788aa8598fbca2b…Patch
    • github.comesengine/DeepSeek-Reasonix/issues/13061Issue tracking
    • github.comesengine/DeepSeek-Reasonix/releases/tag/v2.53.0Patch
    • github.comesengine/DeepSeek-Reasonix/security/advisories/GHSA-7v48-x992-r…related
    • github.comybyu-ieu/agent-security-advisories/blob/main/deepseek-reasonix/…Exploit
    • vuldb.comCVE-2026-123653 | CVE Analysis and ReportThird-party advisory
    • vuldb.comSubmit #1033134 | esengine DeepSeek-Reasonix 1.17.8 CWE-1427 Improper Neutralization of Input Used for LLM PromptingThird-party advisory
    • vuldb.comVDB-431772 | esengine DeepSeek-Reasonix doc.go discoverDocs llm prompting inputVulnerability database, Technical description
    • vuldb.comVDB-431772 | CTI Indicators (IOB, IOC, IOA)signature, Permissions required

    Changes to this CVE

    Who changed this CVE and when: NVD (analysis, affected products, CVSS), the CVE publisher (CNA) and additional providers such as CISA (ADP).

    1. ReceivedVulDB

      CVSS V4.0: AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P

      CVSS V3.1: AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:L

      CVSS V2: (AV:N/AC:L/Au:N/C:P/I:P/A:P)

      Weakness type: CWE-349

      Description added or changed

      Show 16 original changes
      Individual changes of this event as published by NVD
      TypeActionBeforeAfter
      Descriptionadded
      —
      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.
      CVSSadded
      —
      AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
      CVSSadded
      —
      AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:L
      CVSSadded
      —
      (AV:N/AC:L/Au:N/C:P/I:P/A:P)
      Weakness type (CWE)added
      —
      CWE-349
      Affected versions (publisher)added
      —
      New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/123xxx/CVE-2026-123653.json">CVE-2026-123653</a>
      Referenceadded
      —
      https://github.com/esengine/DeepSeek-Reasonix/
      Referenceadded
      —
      https://github.com/esengine/DeepSeek-Reasonix/commit/4ca33493a673c2788aa8598fbca2b2f47a69e1b8
      Referenceadded
      —
      https://github.com/esengine/DeepSeek-Reasonix/issues/13061
      Referenceadded
      —
      https://github.com/esengine/DeepSeek-Reasonix/releases/tag/v2.53.0
      Referenceadded
      —
      https://github.com/esengine/DeepSeek-Reasonix/security/advisories/GHSA-7v48-x992-r5w7
      Referenceadded
      —
      https://github.com/ybyu-ieu/agent-security-advisories/blob/main/deepseek-reasonix/deepseek-reasonix-agents-md-prompt-injection-command-execution.md
      Referenceadded
      —
      https://vuldb.com/cve/CVE-2026-123653
      Referenceadded
      —
      https://vuldb.com/submit/1033134
      Referenceadded
      —
      https://vuldb.com/vuln/431772
      Referenceadded
      —
      https://vuldb.com/vuln/431772/cti

      Source identifier: cna@vuldb.com

    Embed badge

    Show the severity and KEV status of this vulnerability on your site – with a link back here. The image is updated hourly.

    Badge preview for CVE-2026-123653
    <a href="https://intel.neosec.eu/en/cve/CVE-2026-123653"><img src="https://intel.neosec.eu/badge/cve/CVE-2026-123653.svg?lang=en" alt="CVE-2026-123653 – NEOSEC Intel" height="20"></a>