Langflow has Remote Code Execution in CSV Agent

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

9.8 · CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

EPSS

• CVE-2026-27966: 35.25% estimated exploitation activity in the next 30 days; percentile 98.45 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

1. Summary 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).

2. Description

2.1 Intended Functionality When building a flow such as *ChatInput → CSVAgent → ChatOutput*, users can attach an LLM and specify a CSV file path. The CSV Agent then provides capabilities to query, summarize, or manipulate the CSV content using an LLM-driven agent.

2.2 Root Cause In `src/lfx/src/lfx/components/langchain_utilities/csv_agent.py`, the CSV Agent is instantiated as follows: ```python agent_kwargs = { "verbose": self.verbose, "allow_dangerous_code": True,

hardcoded } agent_csv = create_csv_agent(..., **agent_kwargs) ``` Because `allow_dangerous_code` is hardcoded to `True`, LangChain automatically enables the `python_repl_ast` tool. Any LLM…

Published by the source

27 Feb 2026, 15:47 UTC

Last modified by the source

27 Oct 2026, 17:45 UTC

Source last checked

28 Oct 2026, 06:05 UTC

1. Revision 5 · amended · 28 Oct 2026

   Amended from osv record GHSA-3645-fxcv-hqr4

2. Revision 4 · amended · 27 Oct 2026

   Amended from ghsa record GHSA-3645-fxcv-hqr4

3. Revision 3 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-3645-fxcv-hqr4

4. Revision 2 · amended · 24 Oct 2026

   Amended from osv record GHSA-3645-fxcv-hqr4

5. Revision 1 · created · 23 Oct 2026

   Published from ghsa record GHSA-3645-fxcv-hqr4

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-27966

Advisory: Langflow has Remote Code Execution in CSV Agent
IDs: CVE-2026-27966, GHSA-3645-fxcv-hqr4
Record: https://patchnext.com/advisories/cve-2026-27966 (revision 5, source checked 28 Oct 2026, 06:05 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Critical (CVSS 9.8)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor response not established. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI langflow: affected <= 1.8.0rc2

## Suggested inspection (read-only)
- `python -m pip show langflow`: prints the installed version. Run with the environment that serves production active.

## Supported action
No complete vendor fix is recorded. Follow the primary source's mitigation guidance and check this record again before closing anything.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on langflow.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://github.com/advisories/GHSA-3645-fxcv-hqr4 (GitHub-reviewed advisory GHSA-3645-fxcv-hqr4 lists affected ranges: PyPI langflow >=0 <=1.8.0rc2)
- Verified: https://osv.dev/vulnerability/GHSA-3645-fxcv-hqr4 (OSV record GHSA-3645-fxcv-hqr4 lists affected ranges: PyPI langflow >=0 <=1.8.0rc2)

Commands are suggestions: review each one before running it.