BlackTreeCVE Intelligence
← Back to the CVE catalogue
Full vulnerability report · 2026
CVE-2026-105697High confidence

Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration

langflow-ai · langflow

Official source article: GitHub GHSA-W794-RJ3P-XV45 ↗. Check the applicable product and release in the original source.

9.9CriticalCVSS 3.1
Recommended action
Within 7 days

Critical technical severity; prioritise exposed affected systems while verifying vendor guidance.

Fix not verified
R
Operational reassessment

Published severity in operational context

Open reassessment dashboard →
Published severityCriticalOperational priority:Critical, unchanged from published severity.unchanged

Evidence used

  • No CISA KEV confirmation is currently recorded.
  • EPSS is 0.40% for the current model date.

Compensating controls

  • Restrict the affected network interface to trusted sources where business-safe.
  • Monitor vendor guidance and exploitation sources for a material change.

Verification

  1. Confirm that the asset runs langflow-ai langflow and falls inside the recorded affected range.
  2. Recheck the vendor advisory before scheduling a change because no verified fixed version is currently retained.
  3. Validate exposure, authentication requirements and compensating controls in the actual environment.
  4. Reopen this reassessment when CVSS, KEV, EPSS, exploit evidence or remediation changes.
Mitigation target: Within 3 daysRemediation target: Within 90 days

This automated reassessment organises public evidence. It does not know asset exposure, business impact or control effectiveness and does not replace CVSS or a human risk decision.

Open-source package ranges6 source-attributed ranges

These OSV and GitHub advisory ranges apply only to the named package and ecosystem. A listed fixed version is not a universal product patch or proof that an update is installed.

Ecosystem and packageAffected rangeFirst fixed versionEvidence
PyPIlangflowECOSYSTEM: introduced 1.1.2; fixed 1.10.31.10.3OSV record ↗aggregator derived · 7 Oct 2026
PyPIlangflow-baseECOSYSTEM: introduced 0.1.2; fixed 0.10.30.10.3OSV record ↗aggregator derived · 7 Oct 2026
PyPIlfxECOSYSTEM: introduced 0; fixed 1.10.31.10.3OSV record ↗aggregator derived · 7 Oct 2026
piplangflow>= 1.1.2, < 1.10.31.10.3GitHub advisory ↗upstream repository advisory · 7 Oct 2026
piplangflow-base>= 0.1.2, < 0.10.30.10.3GitHub advisory ↗upstream repository advisory · 7 Oct 2026
piplfx< 1.10.31.10.3GitHub advisory ↗upstream repository advisory · 7 Oct 2026
Optional official sources

National CERT insights
?CERT means Computer Emergency Response Team; CSIRT is the closely related term Computer Security Incident Response Team.

Choose official national sources for this report. Each advisory shows its original language. Your selection is remembered on this device and included in shared links.

Official European source

ENISA European Vulnerability Database

Official EUVD identifiers, advisory evidence and known-exploited context. Missing fields are not treated as evidence of low risk.

1 current
ENISA EUVD identifier

EUVD-2026-92788

No EUVD known-exploited evidence

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.

EUVD state
Present in the current official mapping
Known exploitation
Not present in the current ENISA EUVD known-exploited dataset. This is not proof of no exploitation.
ENISA score
9.9 · CVSS 3.1
Advisory evidence
No linked advisory details stored yet
Recommended actionWithin 7 days

Critical technical severity; prioritise exposed affected systems while verifying vendor guidance.

Fix not verified
01

What, why and how

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.

What

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.

Why

Untrusted input is incorporated into an operating-system command without safe parameter handling.

How

An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.

What

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.

Why

Untrusted input is incorporated into an operating-system command without safe parameter handling.

How

An attacker operating through a network path may attempt exploitation with low privileges. If successful, the issue may cause the confidentiality, integrity or availability impact described by the vendor.

02

Exploit reality and attack path

CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.

Observed exploitation
?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.
No confirmed evidence

No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.

Public PoC / exploit material
?Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.
None recorded

No exploit-tagged reference or CISA SSVC proof-of-concept state is currently recorded. Research may still exist outside the structured feeds.

Likely attack path
a network path → Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') → cause the confidentiality, integrity or availability impact described by the vendor
Attack surface
Network
Privileges required
Low: a basic authenticated account is required
User interaction
None
Attack complexity
Low: no specialised conditions are recorded
Security boundary
Changed: exploitation can affect a different security authority
Weakness
?CWE means Common Weakness Enumeration: a standard category for the underlying weakness.
CWE-78 ↗

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

CVSS vector
?CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity.
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Common Vulnerability Scoring System 3.1: the compact vector below is decoded into plain language.

AVNetworkAttack vector: The vulnerable component can be reached over a network.ACLowAttack complexity: No specialised conditions are required beyond attacker-controlled input.PRLowPrivileges required: The attacker needs basic user-level privileges.UINoneUser interaction: No action by another user is required.SChangedScope: The attack can affect a component governed by a different security authority.CHighConfidentiality impact: A successful attack can cause a major loss.IHighIntegrity impact: A successful attack can cause a major loss.AHighAvailability impact: A successful attack can cause a major loss.
Post-exploitation / living off the land
Stolen credentials, tokens and legitimate administration functions may provide continued access without deploying a large custom toolset.
NetworkCWE-78
A

Official authority intelligence

Only matched European and national findings are included. Language selectors and unavailable sources are omitted.

ENISA EUVD · EUVD-2026-92788Official EUVD mapping

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.

Official EUVD record ↗
BSI · German · WID-SEC-2026-3616Langflow: Mehrere Schwachstellen

Ein entfernter, authentisierter Angreifer kann mehrere Schwachstellen in Langflow ausnutzen, um Superuser-Rechte zu erlangen, beliebigen Code auszuführen, Sicherheitsmaßnahmen zu umgehen sowie Daten offenzulegen oder zu manipulieren.

Official advisory ↗
Cyber Security Agency of Singapore · English · CSA-SB-20261007Security Bulletin 7 Oct 2026

The Cyber Security Agency of Singapore included this CVE in its official Security Bulletin 7 Oct 2026, published on 7 October 2026. Open the linked bulletin for the product, severity and reference information published in that issue.

Official advisory ↗
CSIRT Italia · Italian · langflow-disponibili-poc-per-lo-sfruttamento-di-4-vulnerabilitaLangFlow: disponibili PoC per lo sfruttamento di 4 vulnerabilità

In dettaglio, la vulnerabilità identificata tramite la CVE-2026-105741 - di tipo "Authentication Bypass by Spoofing" e con score CVSS v3.1 pari a 7.1 - è dovuta alla mancanza di controlli adeguati nei parametri della funzione get_client_ip . Un attaccante, tramite un header X-Forwarded-For opportunamente predisposto, potrebbe aggirare le restrizioni di accesso riservate alle richieste local-only e ottenere la possibilità di scrivere e/o modificare file di configurazione MCP sul sistema target. La vulnerabilità identificata tramite la CVE-2026-105740 - di tipo "OS Command Injection" e con score CVSS v3.1 pari a 9.9 - è dovuta alla mancanza di adeguata validazione del valore del campo command passato direttamente alla shell bash . Un attaccante autenticato, configurando opportunamente un server MCP, potrebbe sfruttare il trasporto s tdio e far eseguire comandi arbitrari senza isolamento in sandbox. La vulnerabilità identificata tramite la CVE-2026-105699 - di tipo "Authorization Bypass Through User-Controlled Key" e con score CVSS v3.1 pari a 7.1 - deriva da controlli di autorizzazione non adeguati nella gestione delle risorse MCP. Un utente malevolo autenticato, sfruttando un URI opportunamente predisposto inoltrato alla funzione handle_read_resource , potrebbe ottenere l'identificativo del flow ( flow_id ) e il corrispondente nome del file, accedendo quindi a file appartenenti ad altri progetti o tenant. La vulnerabilità identificata tramite la CVE-2026-105697 - di tipo "OS Command Injection" e con score CVSS v3.1 pari a 9.9 - è presente nel trasporto stdio di MCP; in particolare, i valori command e args , controllati dall'utente, possono essere eseguiti sull'host con i privilegi del processo Langflow senza adeguata validazione. Un utente malevolo, in grado di aggiungere un nuovo server MCP o di costruire un flusso con MCP Tools, potrebbe ottenere l'esecuzione di comandi arbitrari sul sistema target.

Official advisory ↗
03

Patch and workaround

Operational remediation based on structured source evidence.

Status
?Patch availability is based on structured fixed-version fields and authoritative update references. If no fix is verified, check the vendor advisory before making a change.
Fix not verified
Affected
  • langflow: >= 1.1.2, < 1.10.3
  • langflow-base: >= 0.1.2, < 0.10.3
  • lfx: < 1.10.3
Fixed
No fixed version is explicitly recorded in the structured CVE data.
Action
No verified patch reference is present in the current structured sources. Check the vendor advisory before making a change.
Workaround
No verified workaround is recorded. If business-safe, reduce exposure to the affected interface and allow only trusted sources until authoritative guidance is available.
04

Evidence and provenance

Published 5 Oct 2026 · Last source change 6 Oct 2026, 14:49 UTC · CWE-78 · Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

CVE recordCVE.org · 5.2
CVSS sourceCNA
EPSS source
?The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.
FIRST · tracked since 2026-10-06
European sourceENISA EUVD · EUVD-2026-92788
Product sourceCNA
Remediation sourceCVE/CNA references
CWE sourceCNA
NVD statusNVD awaiting enrichment

Core structured fields are present and their contributing authorities are shown above.

Material change intelligence

What changed after publication

View recent updates ↗
  1. ENISA EUVD mappingEUVD-2026-92788 was added to the official ENISA EUVD mapping for this CVE.
    Before
    not recorded
    After
    {"euvdId":"EUVD-2026-92788"}
    ENISA EUVD ↗
  2. Catalogue recordCVE added to the BlackTree catalogue.
    CNA ↗
Material fields only · duplicate refreshes suppressed · history retained for the configured operational retention period
CVE published
ENISA EUVD · EUVD-2026-92788↗CVE authority or vendor reference · GitHub GHSA-W794-RJ3P-XV45↗Official CVE record (CNA and ADP data)↗NVD record↗
Technical terms and abbreviations used in this report
CVE
Common Vulnerabilities and Exposures: the public identifier for one disclosed vulnerability.
CVSS
Common Vulnerability Scoring System: a technical severity framework; it is not patching priority by itself.
EPSS
Exploit Prediction Scoring System: FIRST's estimate of the probability that exploitation activity will be observed in the next 30 days; it is a forecast, not confirmation.
CWE
Common Weakness Enumeration: the standard category describing the underlying software or hardware weakness.
CNA
CVE Numbering Authority: an organisation authorised to assign and publish CVE records.
CISA ADP
Cybersecurity and Infrastructure Security Agency Authorized Data Publisher: structured enrichment added to a CVE record.
NVD
National Vulnerability Database: NIST's enrichment service for CVE records.
CERT / CSIRT
A computer security incident response team that publishes warnings or coordinates incident response.
PoC
Proof of concept: public material that demonstrates or helps reproduce exploitation.
CSAF
Common Security Advisory Framework: a machine-readable format for security advisories.
LoTL
Living off the land: abuse of legitimate tools or system functions during an attack.
Free version - for non-commercial use only.CVE-2026-105697 · cve.blacktree.nl