CVE-2026-105697langflow OS Command Injection
Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration
Published Oct 5, 2026 · Updated Oct 15, 2026 · Also known as EUVD-2026-92788, GHSA-w794-rj3p-xv45, PYSEC-2026-4237, PYSEC-2026-4239, PYSEC-2026-4241
Key Facts
Patch in the next maintenance window- CVE-2026-105697 is a critical-severity vulnerability (CVSS 9.9 v3.1) affecting langflow (pypi), langflow-base (pypi), lfx (pypi).
- It is not listed in any known-exploited vulnerabilities catalog. No public exploit code is known.
- EPSS estimates a 0.5% probability of exploitation in the next 30 days.
- Fixed versions are available, including langflow 1.10.3, langflow-base 0.10.3, lfx 1.10.3.
- Brandefense priority: patch in the next maintenance window, because of its high severity, although no exploitation is known.
Scores
CVSS v3.1
9.9
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
EPSS (30-day exploit likelihood)
0.5%
Higher than 39.4% of all scored CVEs
Exploit maturity
None known
ATLAS score
30/100
Publication score, see How it works
Exploitation Verdict
KEV listed
Not listed
Federal due date
None
No federal due date
Ransomware use
Not reported
Attributed actors
None named
Exploit & Defence Guidance
Exploit maturity
None known
Public exploit code
0
Proof-of-concept links
In-the-wild evidence
0
Reports of active use
Advisories And Exploit References
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.
Affected Products
6 affected entries in total| Product | Affected versions | Fixed in |
|---|---|---|
| langflowpypi | >= 1.1.2, >= >= 1.1.2, < 1.10.3 | 1.10.3 |
| langflow-basepypi | >= 0.1.2, >= >= 0.1.2, < 0.10.3 | 0.10.3 |
| lfxpypi | >= < 1.10.3 | 1.10.3 |
Patched Releases
langflow
1.10.3
langflow-base
0.10.3
lfx
1.10.3
Timeline
Publicly disclosed
Oct 5, 2026
Last updated
Oct 15, 2026
Weakness Type
- CWE-78 Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
References
- advisorycve.org · CVERecord
- advisorynvd.nist.gov · CVE-2026-105697
- advisoryGHSA advisory
- othergithub.com · langflow
- otherhttps://github.com/langflow-ai/langflow/commit/eba285edf1dd4a33bf23a9cb8113c991fcdf3d1d
FAQ
Common Questions.
Langflow is a tool for building and deploying AI-powered agents and workflows.
Affected: langflow (pypi) versions >= 1.1.2, >= >= 1.1.2, < 1.10.3; langflow-base (pypi) versions >= 0.1.2, >= >= 0.1.2, < 0.10.3; lfx (pypi) versions >= < 1.10.3. The full list is in the CVE brief.
It is not listed in any known-exploited vulnerabilities catalog.
No, it is not currently listed in the CISA Known Exploited Vulnerabilities catalog.
No public exploit code is known.
Fixed versions are available, including langflow 1.10.3, langflow-base 0.10.3, lfx 1.10.3.
Brandefense priority: patch in the next maintenance window, because of its high severity, although no exploitation is known.
Is CVE-2026-105697 On Your Attack Surface?
Brandefense matches it against the products discovered on your perimeter and opens a finding the day a CVE like this is listed.
Request A Demo