Skip to content
Fencer Intel
critical 9.9

CVE-2026-105740 json

Langflow: Authenticated RCE via MCP Stdio transport allows any user to execute arbitrary OS commands on the server

published last mo. modified last mo. also EUVD-2026-92799

cvss
9.9
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
3.9%
EPSS 3.9% chance of exploitation in 30 days, percentile 90%
public exploits
0
none known, plus a Nuclei check

Summary

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, any authenticated Langflow user can achieve Remote Code Execution (RCE) on the server by adding an MCP server with the "Stdio" transport. The user-supplied command field is passed directly to bash -c "exec {command}" with zero validation, no allowlisting, and no sandboxing. The command executes immediately when the server list is fetched. Additionally, the env field allows arbitrary environment variable injection (e.g., LD_PRELOAD, PATH override). This vulnerability is fixed in 1.9.0.

Patch / fix

  • langflow langflow 1.9.0

Is CVE-2026-105740 in your stack? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

CISA SSVC

Exploitation
Proof of concept is public
Automatable
no
Technical impact
total
Assessed
last mo.

Exploit prediction

3.89% chance of exploitation in the next 30 days, higher than 90% of all scored CVEs (FIRST EPSS, 2026-11-09).

Exploits and checks

  • Nuclei template Langflow 1.8.3 and 1.9.0 - Authenticated MCP Stdio Command Execution nuclei detection template
  • github.com https://github.com/langflow-ai/langflow/security/advisories/GHSA-7w94-79vh-5mr2 referenced PoC, tagged "exploit" by a source, unverified
  • github.com https://github.com/langflow-ai/langflow/security/advisories/GHSA-w794-rj3p-xv45 referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 9.9 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Affected products

  • langflow-ai langflow

Classification

Weakness
  • CWE-78 Improper Neutralization of Special Elements used in an OS Command

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.