CVE-2026-41264
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.
View on NVDAnalysis
Flowise instances prior to 3.1.0 are vulnerable to unauthenticated remote code execution. An attacker can use prompt injection against the CSV Agent node to execute malicious Python commands directly on the server hosting the application. Users should update to the latest version immediately to secure their chatflows.
Severity
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:HCWE-184EPSS
Affects
flowiseai:flowiseTechnical 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.