---
id: CVE-2026-70477
title: >-
  Flowise is a drag & drop user interface to build a customized large language
  model flow
summary: >-
  Flowise is a drag & drop user interface to build a customized large language
  model flow. Prior to 3.1.3, a prompt injection sent to a chatflow using a CSV
  Agent node can cause the LLM to respond with a malicious Python script that
  bypass…
severity: critical
cvss: 9.8
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'
cwe:
  - CWE-94
vendor: flowiseai
product: flowise
affected:
  - flowise < 3.1.3
patched:
  - flowise 3.1.3
published: '2026-08-04'
updated: '2026-09-11'
sourceUpdated: '2026-09-11T21:09:26.917'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-70477'
references:
  - url: >-
      https://github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626c
    label: security-advisories@github.com
  - url: 'https://github.com/FlowiseAI/Flowise/pull/6499'
    label: security-advisories@github.com
  - url: 'https://github.com/FlowiseAI/Flowise/releases/tag/flowise@3.1.3'
    label: security-advisories@github.com
  - url: >-
      https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr
    label: security-advisories@github.com
  - url: >-
      https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
  - url: 'https://github.com/advisories/GHSA-5xvg-pmgg-3mxr'
tags:
  - nvd
  - ghsa
  - npm
epss: 0.00833
epssPercentile: 0.55658
aliases:
  - GHSA-5xvg-pmgg-3mxr
ecosystem: npm
ingestedAt: '2026-08-04T19:41:28.889Z'
---

## Overview

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, a prompt injection sent to a chatflow using a CSV Agent node can cause the LLM to respond with a malicious Python script that bypasses the blocklist validator and executes in an unsandboxed Pyodide environment. The specific flaw exists within the run method of the CSV_Agents class, where untrusted data is used to construct an LLM prompt and the resulting pythonCode is validated by validatePythonCodeForDataFrame before execution. An attacker can leverage this to execute arbitrary code in the context of the service account. This issue is fixed in 3.1.3.

## Affected

- `flowise < 3.1.3`

## Remediation

Upgrade past the affected range:

- `flowise 3.1.3`

## Package advisory (CVE-2026-70477)

Affected packages:

- `flowise <= 3.1.2`
- `flowise-components <= 3.1.2`

Patched in:

- `flowise 3.1.3`
- `flowise-components 3.1.3`

Source: https://github.com/advisories/GHSA-5xvg-pmgg-3mxr