9.8
CRITICAL CVSS 3.1
CVE-2026-70477
Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability
Description

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.

INFO

Published Date :

Aug. 4, 2026, 8:16 p.m.

Last Modified :

Oct. 24, 2026, 3:10 p.m.

Remotely Exploit :

Yes !
Affected Products

The following products are affected by CVE-2026-70477 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

ID Vendor Product Action
1 Flowiseai flowise
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 134c704f-9b21-4f2e-91b3-4a467353bcc0
CVSS 3.1 CRITICAL [email protected]
CVSS 4.0 CRITICAL [email protected]
Solution
Update Flowise to version 3.1.3 or later to fix prompt injection vulnerabilities.
  • Update Flowise to version 3.1.3 or later.
  • Review and sanitize all user inputs.
  • Validate Python code before execution.
References to Advisories, Solutions, and Tools

Here, you will find a curated list of external links that provide in-depth information, practical solutions, and valuable tools related to CVE-2026-70477.

URL Resource
https://github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626c Patch
https://github.com/FlowiseAI/Flowise/pull/6499 Issue Tracking Patch
https://github.com/FlowiseAI/Flowise/releases/tag/[email protected] Release Notes
https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr Vendor Advisory
https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr Vendor Advisory
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-70477 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-70477 weaknesses.

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-70477 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-70477 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • CVE Translated by [email protected]

    Oct. 24, 2026

    Action Type Old Value New Value
    Changed Translation Title: Flowise de FlowiseAI, Description: Flowise es una interfaz de usuario de arrastrar y soltar para construir un flujo de modelo de lenguaje grande personalizado. Antes de la 3.1.3, una inyección de prompt enviada a un chatflow utilizando un nodo de Agente CSV puede hacer que el LLM responda con un script Python malicioso que omite el validador de lista de bloqueo y se ejecuta en un entorno Pyodide sin sandbox. La falla específica existe dentro del método run de la clase CSV_Agents, donde se utilizan datos no confiables para construir un prompt del LLM y el pythonCode resultante es validado por validatePythonCodeForDataFrame antes de la ejecución. Un atacante puede aprovechar esto para ejecutar código arbitrario en el contexto de la cuenta de servicio. Este problema se soluciona en la 3.1.3. Title: Flowise de FlowiseAI, Description: Flowise es una interfaz de usuario de arrastrar y soltar para construir un flujo de modelo de lenguaje grande personalizado. Antes de la 3.1.3, una inyección de prompt enviada a un chatflow utilizando un nodo de Agente CSV puede hacer que el LLM responda con un script Python malicioso que omite el validador de lista de bloqueo y se ejecuta en un entorno Pyodide sin sandbox. La falla específica existe dentro del método run de la clase CSV_Agents, donde se utilizan datos no confiables para construir un prompt del LLM y el pythonCode resultante es validado por validatePythonCodeForDataFrame antes de la ejecución. Un atacante puede aprovechar esto para ejecutar código arbitrario en el contexto de la cuenta de servicio. Este problema se soluciona en la 3.1.3.
  • CVE Translated by [email protected]

    Oct. 23, 2026

    Action Type Old Value New Value
    Added Translation Title: Flowise de FlowiseAI, Description: Flowise es una interfaz de usuario de arrastrar y soltar para construir un flujo de modelo de lenguaje grande personalizado. Antes de la 3.1.3, una inyección de prompt enviada a un chatflow utilizando un nodo de Agente CSV puede hacer que el LLM responda con un script Python malicioso que omite el validador de lista de bloqueo y se ejecuta en un entorno Pyodide sin sandbox. La falla específica existe dentro del método run de la clase CSV_Agents, donde se utilizan datos no confiables para construir un prompt del LLM y el pythonCode resultante es validado por validatePythonCodeForDataFrame antes de la ejecución. Un atacante puede aprovechar esto para ejecutar código arbitrario en el contexto de la cuenta de servicio. Este problema se soluciona en la 3.1.3.
  • Initial Analysis by [email protected]

    Sep. 11, 2026

    Action Type Old Value New Value
    Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
    Added CPE Configuration OR *cpe:2.3:a:flowiseai:flowise:*:*:*:*:*:*:*:* versions up to (excluding) 3.1.3
    Added Reference Type GitHub, Inc.: https://github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626c Types: Patch
    Added Reference Type GitHub, Inc.: https://github.com/FlowiseAI/Flowise/pull/6499 Types: Issue Tracking, Patch
    Added Reference Type GitHub, Inc.: https://github.com/FlowiseAI/Flowise/releases/tag/[email protected] Types: Release Notes
    Added Reference Type CISA-ADP: https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr Types: Vendor Advisory
    Added Reference Type GitHub, Inc.: https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr Types: Vendor Advisory
  • CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0

    Aug. 05, 2026

    Action Type Old Value New Value
    Added Reference https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr
    Added SSVC {'id': 'CVE-2026-70477', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'yes'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-08-05T13:51:06.061832Z'}
  • New CVE Received by [email protected]

    Aug. 04, 2026

    Action Type Old Value New Value
    Added Affected [{'vendor': 'FlowiseAI', 'product': 'Flowise', 'versions': [{'status': 'affected', 'version': '< 3.1.2'}]}]
    Added Description 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.
    Added CVSS V4.0 AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
    Added CWE CWE-94
    Added Reference https://github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626c
    Added Reference https://github.com/FlowiseAI/Flowise/pull/6499
    Added Reference https://github.com/FlowiseAI/Flowise/releases/tag/[email protected]
    Added Reference https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.