Critical severity · published Feb 26, 2026
CVE-2026-27966
Langflow has Remote Code Execution in CSV Agent
9.8
CVSS
35.2%
EPSS
No
On KEV
Description
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes `allow_dangerous_code=True`, which automatically exposes LangChain’s Python REPL tool (`python_repl_ast`). As a result, an attacker can execute arbitrary Python and OS commands on the server via prompt injection, leading to full Remote Code Execution (RCE). Version 1.8.0 fixes the issue.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)35.2% · higher than 98% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LA
langflow · langflow-ai
< 1.8.0 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-27966
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-27966
Patch
https://github.com/langflow-ai/langflow/commit/d8c6480daa17b2f2af0b5470cdf5c3d28dc9e508
Exploit
https://github.com/langflow-ai/langflow/security/advisories/GHSA-3645-fxcv-hqr4
More from langflow
9.8
CVE-2026-33017
Langflow has Unauthenticated Remote Code Execution via Public Flow Build Endpoint
9.8
CVE-2025-3248
Langflow < 1.3.0 Unauthenticated RCE via /api/v1/validate/code
8.4
CVE-2026-55255
Langflow: IDOR Vulnerability in `/api/v1/responses` Endpoint Allows Authenticated Attackers to Access Another User's Flow
9.9
CVE-2026-105740
Langflow: Authenticated RCE via MCP Stdio transport allows any user to execute arbitrary OS commands on the server
9.9
CVE-2026-105697
Langflow: OS command injection (RCE) via arbitrary command in MCP stdio server configuration