Skip to content
LLMHigh

CVE-2026-70477: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.…

Occurred
Aug 4, 2026
Published
Aug 4, 2026
Source
NVD CVE

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 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.

Tags

  • CVE
  • CVE-2026-70477
  • cvss:CRITICAL

Classification

Category confidence: 95%
Severity confidence: 90%

Rationale: Prompt injection vulnerability in LLM flow allows arbitrary code execution in unsandboxed environment.

Classifier: Qwen/Qwen3.5-35B-A3B-FP8

Visit source