Skip to main content

IBM Langflow OSS CVE-2026-7663

| EUVDEUVD-2026-40384 CRITICAL
Improper Authorization (CWE-285)
2026-06-30 ibm GHSA-5wjx-cxqm-p8r4
9.8
CVSS 3.1 · NVD
Share

Severity by source

Vendor (ibm) PRIMARY
CRITICAL
qualitative
NVD
9.8 CRITICAL
AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
vuln.today AI
9.8 CRITICAL

Network-reachable MCP endpoint with no authentication or interaction (AV:N/AC:L/PR:N/UI:N); missing authorization yields unauthorized resource access and operation execution, supporting high confidentiality and integrity, with availability high retained per vendor rating.

3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Primary rating from Vendor (ibm).

CVSS VectorNVD

Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

Lifecycle Timeline

5
Analysis Updated
Jul 02, 2026 - 18:29 vuln.today
v3 (cvss_changed)
Analysis Updated
Jul 02, 2026 - 18:29 vuln.today
v2 (cvss_changed)
Re-analysis Queued
Jul 02, 2026 - 18:22 vuln.today
cvss_changed
CVSS changed
Jul 02, 2026 - 18:22 NVD
9.1 (CRITICAL) 9.8 (CRITICAL)
Analysis Generated
Jun 30, 2026 - 19:53 vuln.today

DescriptionNVD

IBM Langflow OSS 1.0.0 through 1.9.6 could allow unauthenticated attackers to access protected MCP project resources and execute MCP operations due to improper authorization enforcement in the Streamable MCP transport endpoint.

AnalysisAI

Improper authorization enforcement in IBM Langflow OSS 1.0.0 through 1.9.6 lets unauthenticated remote attackers reach protected MCP (Model Context Protocol) project resources and invoke MCP operations through the Streamable MCP transport endpoint. Because the flaw bypasses authentication entirely on a network-facing endpoint and is rated CVSS 9.8 with full confidentiality, integrity, and availability impact, any exposed Langflow instance is at risk. There is no public exploit identified at time of analysis, and the EPSS probability is low (0.24%, 15th percentile), indicating exploitation has not yet become widespread.

Technical ContextAI

Langflow OSS is an open-source, IBM-maintained low-code visual framework for building LLM-driven agents and workflows, which exposes tools and data to AI clients via the Model Context Protocol (MCP). The vulnerability lives in the Streamable HTTP MCP transport endpoint, the server-sent/streaming channel MCP clients use to call project-scoped tools and resources. The root cause is CWE-285 (Improper Authorization): the endpoint fails to enforce the authorization checks that should gate access to a given MCP project, so requests that should require an authenticated, authorized identity are honored regardless. In effect the authorization decision is missing or incorrectly applied at the transport layer, allowing operation-level access to resources scoped to other users' or projects' MCP servers.

RemediationAI

Patch available per vendor advisory: IBM has released a fix, so upgrade Langflow OSS to the vendor-specified fixed release above 1.9.6 as documented at https://www.ibm.com/support/pages/node/7277570 (consult that advisory for the exact patched version, which is not enumerated in the available data). As an interim compensating control until patching, restrict network reachability of the Streamable MCP transport endpoint - place Langflow behind an authenticating reverse proxy or gateway that enforces identity before requests reach the endpoint, and block direct inbound access to the MCP port from untrusted networks; the trade-off is that legitimate remote MCP clients must be routed through the proxy and re-authenticated. Where MCP project exposure is not required, disable or do not expose the MCP server feature for sensitive projects, accepting the loss of remote MCP tool access. Avoid exposing Langflow directly to the internet.

CVE-2026-9198 CRITICAL POC
9.8 Jul 17

Unauthenticated remote code execution in IBM Langflow OSS versions 1.0.0 through 1.10.0 lets any network-reachable attac

CVE-2026-19295 CRITICAL POC
9.9 Aug 28

Authenticated command injection in IBM Langflow OSS 1.0.0 through 1.11.1 lets any logged-in flow user escalate to arbitr

CVE-2026-18729 HIGH POC
8.8 Aug 28

Remote code execution in IBM Langflow OSS 1.0.0 through 1.11.1 allows a network-accessible authenticated attacker with l

CVE-2026-10561 CRITICAL
10.0 Jun 22

Unauthenticated remote code execution in IBM Langflow OSS versions 1.0.0 through 1.9.3 allows attackers to fully comprom

CVE-2026-9135 CRITICAL
9.9 Jul 17

Arbitrary Python code execution in IBM Langflow OSS 1.0.0 through 1.10.0 (Langflow versions up to 1.9.2) allows authenti

CVE-2026-8476 CRITICAL
9.9 Jul 17

Remote code execution in IBM Langflow OSS 1.0.0 through 1.10.0 allows attackers to run arbitrary code by planting a mali

CVE-2026-8481 CRITICAL
9.9 Jul 17

Authenticated remote code execution in IBM Langflow OSS 1.0.0 through 1.10.0 lets any logged-in user run arbitrary Pytho

CVE-2026-8859 CRITICAL
9.9 Jul 17

Arbitrary file write in IBM Langflow OSS 1.0.0 through 1.10.0 lets an attacker who controls an external HTTP server plan

CVE-2026-12946 CRITICAL
9.9 Jul 30

Remote code injection in IBM Langflow OSS versions 1.0.0 through 1.10.0 allows an authenticated remote attacker to execu

CVE-2026-13435 CRITICAL
9.9 Jul 30

Remote code execution in IBM Langflow OSS 1.0.0 through 1.10.1 stems from improper input validation in the PythonREPL sa

CVE-2026-8635 CRITICAL
9.9 Jul 17

Privilege escalation to remote code execution in IBM Langflow OSS 1.0.0 through 1.10.0 allows an authenticated user to e

CVE-2026-7873 CRITICAL
9.9 Jun 30

Code injection in IBM Langflow OSS versions 1.0.0 through 1.10.0 lets an authenticated user execute arbitrary operating-

Share

CVE-2026-7663 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy