CriticalCVE-2026-105697

    Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration (CVE-2026-105697)

    Published Last modified Sources: OSV, CVE.org, Hersteller

    What is affected, what to do

    Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and (before 1.10.3) wrapped in bash -c "exec {command} ...".

    An exploit is publicly available. Update Langflow-ai Lfx to version 1.10.3.

    Affected
    • Langflow gte 1.1.2, < 1.10.3..*
    • Langflow-ai Langflow-base gte 0.1.2, < 0.10.3..*
    • Langflow-ai Lfx lt *..1.10.3
    Fixed in
    • Langflow-ai Lfx 1.10.3

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

    Metrics

    9.9

    Priority

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

    Source: Vendor (CNA), CVSS v3

    9.9

    CVSS v3

    Severity Critical on the scale from 0 to 10.

    Source: OSV, CVE.org, Hersteller

    1.0 %

    EPSS score

    Low — model estimates < 1% exploitation likelihood.

    Source: FIRST EPSS, percentile 61.2

    Show all metrics
    Severity
    Critical
    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
    109.47 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
    9.9 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
    9.9
    EPSS score

    The EPSS score is the absolute model output for an individual vulnerability: the estimated probability of real-world exploitation within the next 30 days, expressed as a value between 0 and 1 (i.e. 0 % to 100 %). A score of 0.42 means „the model estimates a 42 % chance of real-world exploitation within 30 days“.

    Read in glossary
    1.0 %
    Low — model estimates < 1% exploitation likelihood.
    EPSS percentile

    The EPSS percentile is the relative position of a vulnerability within all EPSS-scored CVEs, expressed as a value between 0 and 1. A percentile of 0.90 means „this CVE has a higher EPSS score than 90 % of all other scored CVEs“. Unlike the EPSS score, it is not a probability — but a positioning within a ranking.

    Read in glossary
    61.2
    High — this CVE ranks above the median of all CVEs scored today (rank ≥ 36%).
    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
    CISA assessment (SSVC)
    Exploitation: none known · not automatable · Technical impact: total
    Source: CISA Vulnrichment, as of 6 October 2026
    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-78

    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
    High technical severity: assess and remediate the vulnerability in vulnerability handling under Art. 21(2)(e) NIS2 and document the decision.
    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

    Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and (before 1.10.3) wrapped in bash -c "exec {command} ...". Any user able to reach the MCP server settings ("Settings → MCP Servers → Add MCP Server", POST/PATCH /api/v2/mcp/servers/{server_name}) or to build a flow with the MCP Tools component could add a "server" whose command is an arbitrary OS command (touch, rm -rf, a reverse shell, ...). The command runs on the Langflow host as the Langflow process user as soon as Langflow tries to connect to the server (listing servers, loading tools, running the flow) — even when the UI then reports that the stdio server failed to start. With the default LANGFLOW_AUTO_LOGIN=true, GET /api/v1/auto_login hands out a token without credentials, so on an exposed instance running the default configuration this is reachable without an account. AUTO_LOGIN is documented as a development-only setting; with it disabled, any authenticated (non-admin) user can exploit it. This issue is fixed in Langflow 1.10.3, langflow-base 0.10.3, and lfx 1.10.3.

    Source: OSV (Open Source Vulnerabilities), cvelistv5, GitHub Security Advisories, 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
    langflow-ailangflow
    • ≥ 1.1.2, < 1.10.3
    • —
    langflow-ailangflow-base
    • ≥ 0.1.2, < 0.10.3
    • —
    langflow-ailfx
    • < 1.10.3
    • 1.10.3
    pypilfx
    • 1.10.2rc4
    • 1.10.2
    • 0.1.8
    • 0.4.2
    • 0.1.7
    • 1.10.3rc0
    • 0.1.9
    • 0.1.11
    • 0.3.0rc2
    • 1.10.0
    • 0.1.13
    • 0.3.0rc4
    • 0.1.1
    • 0.1.10
    • 1.10.0rc0
    • 0.2.1
    • 0.1.3
    • 0.4.6
    • 0.4.3
    • 0.3.0rc6
    • 0.4.1
    • 0.4.5
    • 0.1.6
    • 0.3.4
    • 0.3.0rc1
    • 0.1.5
    • 0.3.1
    • 0.3.0rc0
    • 0.3.2
    • 0.4.0
    • 0.1.4
    • 1.10.1rc3
    • 0.3.3rc0
    • 0.1.0
    • 0.3.0rc5
    • 1.10.1rc0
    • 0.3.0
    • 0.2.2
    • 0.2.0
    • 1.10.1
    • 0.4.6rc0
    • 0.3.0rc3
    • 0.1.2
    • 0.4.3rc0
    • 0.4.4
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —

    Vendors and products

    Weakness classes (CWE)

    • CWE-78Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

      Base

      The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.

      Entry at MITRE CWE-78

    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
    CIRCL Sightingsgithub.com (opens in a new tab)PoC (publicly reported)reported, not verified

    References & sources

    • github.comlangflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45x_refsource_CONFIRM
    • github.comlangflow-ai/langflow/pull/12290x_refsource_MISC
    • github.comlangflow-ai/langflow/pull/14036x_refsource_MISC
    • github.comlangflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcd…x_refsource_MISC
    • github.comlangflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc…x_refsource_MISC
    • github.comlangflow-ai/langflow/releases/tag/v1.10.3x_refsource_MISC
    • NVD (NIST)vuln/detail/CVE-2026-105697advisory
    • github.comlangflow-ai/langflowpackage
    • github.comlangflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2x_refsource_MISC
    • ox.securityblog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-a…x_refsource_MISC
    • ox.securityblog/the-mother-of-all-ai-supply-chains-critical-systemic-vulne…x_refsource_MISC
    • pypi.orgproject/langflowpackage
    • GitHub Security Advisoriesadvisories/GHSA-w794-rj3p-xv45advisory
    • pypi.orgproject/langflow-basepackage
    • pypi.orgproject/lfxpackage

    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. Record modifiedGitHub

      Show 3 original changes
      Individual changes of this event as published by NVD
      TypeActionBeforeAfter
      Referenceadded
      —
      https://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2
      Referenceadded
      —
      https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem
      Referenceadded
      —
      https://www.ox.security/blog/the-mother-of-all-ai-supply-chains-critical-systemic-vulnerability-at-the-core-of-the-mcp

      Source identifier: security-advisories@github.com

    2. Record modifiedCISA ADP

      CISA assessment (SSVC): exploitation: none known, automatable: no

      Show the original change
      Individual changes of this event as published by NVD
      TypeActionBeforeAfter
      SSVC assessmentadded
      —
      {"id":"CVE-2026-105697","role":"CISA Coordinator","options":[{"exploitation":"none"},{"automatable":"no"},{"technicalImpact":"total"}],"version":"2.0.3","timestamp":"2026-10-06T14:36:02.678305Z"}

      Source identifier: 134c704f-9b21-4f2e-91b3-4a467353bcc0

    3. ReceivedGitHub

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

      Weakness type: CWE-78

      Description added or changed

      Show 10 original changes
      Individual changes of this event as published by NVD
      TypeActionBeforeAfter
      Descriptionadded
      —
      Langflow is a tool for building and deploying AI-powered agents and workflows. Before Langflow 1.10.3, the MCP stdio transport launched whatever command / args a user put in an MCP server configuration, with no allowlist and (before 1.10.3) wrapped in bash -c "exec {command} ...". Any user able to reach the MCP server settings ("Settings → MCP Servers → Add MCP Server", POST/PATCH /api/v2/mcp/servers/{server_name}) or to build a flow with the MCP Tools component could add a "server" whose command is an arbitrary OS command (touch, rm -rf, a reverse shell, ...). The command runs on the Langflow host as the Langflow process user as soon as Langflow tries to connect to the server (listing servers, loading tools, running the flow) — even when the UI then reports that the stdio server failed to start. With the default LANGFLOW_AUTO_LOGIN=true, GET /api/v1/auto_login hands out a token without credentials, so on an exposed instance running the default configuration this is reachable without an account. AUTO_LOGIN is documented as a development-only setting; with it disabled, any authenticated (non-admin) user can exploit it. This issue is fixed in Langflow 1.10.3, langflow-base 0.10.3, and lfx 1.10.3.
      CVSSadded
      —
      AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
      Weakness type (CWE)added
      —
      CWE-78
      Affected versions (publisher)added
      —
      New affected value received. <a href="https://github.com/CVEProject/cvelistV5/blob/main/cves/2026/105xxx/CVE-2026-105697.json">CVE-2026-105697</a>
      Referenceadded
      —
      https://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d
      Referenceadded
      —
      https://github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0
      Referenceadded
      —
      https://github.com/langflow-ai/langflow/pull/12290
      Referenceadded
      —
      https://github.com/langflow-ai/langflow/pull/14036
      Referenceadded
      —
      https://github.com/langflow-ai/langflow/releases/tag/v1.10.3
      Referenceadded
      —
      https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45

      Source identifier: security-advisories@github.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-2026-105697
    <a href="https://intel.neosec.eu/en/cve/CVE-2026-105697"><img src="https://intel.neosec.eu/badge/cve/CVE-2026-105697.svg?lang=en" alt="CVE-2026-105697 – NEOSEC Intel" height="20"></a>