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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
flowisenpm | < 3.1.3 | 3.1.3 |
flowise-componentsnpm | < 3.1.3 | 3.1.3 |
Affected products
1Patches
Vulnerability mechanics
References
5- github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626cnvdPatchWEB
- github.com/FlowiseAI/Flowise/pull/6499nvdIssue TrackingPatchWEB
- github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxrnvdVendor AdvisoryWEB
- github.com/advisories/GHSA-5xvg-pmgg-3mxrghsaADVISORY
- github.com/FlowiseAI/Flowise/releases/tag/[email protected]nvdRelease NotesWEB
News mentions
1- ⚡ Weekly Recap: Chinese Spy Proxy, AI Agents Go Off-Task, Router Backdoors and MoreThe Hacker News · Aug 31, 2026