CVE-2026-41264

CRITICAL

Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability

Title source: cna
STIX 2.1

Exploitation Summary

EIP tracks 1 public exploit for CVE-2026-41264. PoCs published by zdi-disclosures, Takahiro Yokoyama, including Metasploit module exploits/multi/http/flowise_auth_rce_cve_2026_41264.

AI-analyzed exploit summary This Metasploit module exploits a prompt injection vulnerability in FlowiseAI Flowise's CSV Agent, allowing remote code execution by leveraging improper sandboxing of LLM-generated Python scripts. The exploit creates a malicious chatflow and triggers payload execution via a crafted question.

Description

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.0, the specific flaw exists within the run method of the CSV_Agents class. The issue results from the lack of proper sandboxing when evaluating an LLM generated python script. An attacker can leverage this vulnerability to execute code in the context of the user running the server. Using prompt injection techniques, an unauthenticated attacker with the ability to send prompts to a chatflow using the CSV Agent node may convince an LLM to respond with a malicious python script that executes attacker controlled commands on the Flowise server. This vulnerability is fixed in 3.1.0.

Exploits (1)

metasploit WORKING POC EXCELLENT
by zdi-disclosures, Takahiro Yokoyama · rubypocwin
https://github.com/rapid7/metasploit-framework/blob/master/modules/exploits/multi/http/flowise_auth_rce_cve_2026_41264.rb

This Metasploit module exploits a prompt injection vulnerability in FlowiseAI Flowise's CSV Agent, allowing remote code execution by leveraging improper sandboxing of LLM-generated Python scripts. The exploit creates a malicious chatflow and triggers payload execution via a crafted question.

Classification
Working Poc 100%
Attack Type
Rce
Complexity
Moderate
Reliability
Reliable
Target: FlowiseAI Flowise versions 1.3.0 to 3.0.13
Auth required
Prerequisites: Flowise API key with chatflows:create permission · Attacker-controlled OLLAMA API endpoint · Valid OLLAMA model name
mistral-large-3 · analyzed Jul 01, 2026 Full analysis →

References (1)

Core 1
Core References

Scores

CVSS v3 9.8
EPSS 0.0144
EPSS Percentile 70.5%
Attack Vector NETWORK
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CISA SSVC

Vulnrichment
Exploitation poc
Automatable no
Technical Impact total

Details

CWE
CWE-184
Status published
Products (4)
flowiseai/flowise < 3.1.0
FlowiseAI/Flowise < 3.1.0
npm/flowise 0 - 3.1.0npm
npm/flowise-components 0 - 3.1.0npm
Published Apr 23, 2026
Tracked Since Apr 24, 2026