- CVSS
- CRITICAL · 9.8v3.1CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- Published
- 2026-08-04
- Weakness
- CWE-94
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-70477
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.
References
- https://github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626c
- https://github.com/FlowiseAI/Flowise/pull/6499
- https://github.com/FlowiseAI/Flowise/releases/tag/[email protected]
- https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr
- https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-70477 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.