PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-105697 langflow-ai CVE debrief

Langflow, a Python package available on PyPI, had a vulnerability in versions before 1.10.3 that allowed for OS command injection via arbitrary commands in MCP stdio server configurations. This issue was exploitable by users with access to MCP server settings or the MCP Tools component, potentially leading to remote code execution as the Langflow process user. The vulnerability was fully fixed in Langflow version 1.10.3.

Vendor
langflow-ai
Product
langflow
CVSS
CRITICAL 9.9
CISA KEV
Not listed in stored evidence
Original CVE published
2026-10-07
Original CVE updated
2026-10-07
Advisory published
2026-10-07
Advisory updated
2026-10-07

Who should care

Langflow users, administrators of Langflow instances, and security teams responsible for monitoring and patching vulnerabilities in Python packages should prioritize patching to version 1.10.3 or later. They should also restrict access to MCP server settings and the MCP Tools component, and monitor for suspicious activity on Langflow instances to prevent potential exploitation and minimize operational impacts.

Why it matters

CVE-2026-105697 is a critical vulnerability in Langflow that allows for OS command injection, potentially leading to remote code execution. Langflow users and administrators should prioritize patching to version 1.10.3 or later and restrict access to MCP server settings and the MCP Tools component.

  • Remote code execution as the Langflow process user
  • Potential for data breaches or system compromise
  • Need for immediate patching or mitigation
  • Verification of Langflow instance security

Technical summary

The MCP stdio transport in Langflow launched user-supplied commands without validation, allowing for OS command injection. This was exploitable by users with access to MCP server settings or the MCP Tools component. The issue was fully fixed in Langflow version 1.10.3, which validated user input and restricted command execution. Langflow users should upgrade to version 1.10.3 or later to prevent exploitation. The vulnerability allowed for remote code execution as the Langflow process user, potentially leading to data breaches or system compromise.

Defensive priority

High

Recommended defensive actions

  • Upgrade Langflow to version 1.10.3 or later
  • Restrict access to MCP server settings and MCP Tools component
  • Monitor for suspicious activity on Langflow instances
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented
  • Confirm whether affected product deployments exist in managed environments and assign an owner for follow-up

Evidence notes

The vulnerability was reported by an unknown source and documented in the CVE record and NVD entry. The issue was fixed in Langflow version 1.10.3. However, details about the exploitation and impact are limited. To verify, defenders should review the official advisory, assess their exposure, and check for suspicious activity on Langflow instances.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-105697 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-105697

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-105697 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-105697

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

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

    Unverified legacy reference

    URL: https://storage.googleapis.com/osv-vulnerabilities/PyPI/GHSA-w794-rj3p-xv45.json

    osv_dev

  • Source reference

    Unverified legacy reference

    URL: https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45

    Supplemental source

  • Source reference

    Unverified legacy reference

    URL: https://github.com/langflow-ai/langflow/pull/12290

    Supplemental source

  • Source reference

    Unverified legacy reference

    URL: https://github.com/langflow-ai/langflow/pull/14036

    Supplemental source

  • Source reference

    Unverified legacy reference

    URL: https://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d

    Supplemental source

  • Source reference

    Unverified legacy reference

    URL: https://github.com/langflow-ai/langflow/commit/efbc4a16e639409d938a4883463d27ef0bc637a0

    Supplemental source

  • Source reference

    Unverified legacy reference

    URL: https://github.com/langflow-ai/langflow

    Supplemental source

  • Source reference

    Unverified legacy reference

    URL: https://github.com/langflow-ai/langflow/releases/tag/v1.10.3

    Supplemental source

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.