Vulnerability · Published Aug 4, 2026 · Assigned by GitHub_M

CVE-2026-70477Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability

Critical 9.5

In plain English

A critical-severity code injection in Flowise from FlowiseAI. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.8% (higher than 57% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 4.0)9.5Critical

Exploit odds (30 days)0.8%top 42.8% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
npm	flowise	3.1.3	GHSA-5xvg-pmgg-3mxr
npm	flowise-components	3.1.3	GHSA-5xvg-pmgg-3mxr

Affected products (as reported)

Vendor	Product	Versions
FlowiseAI	Flowise	< 3.1.2

Weakness: CWE-94 · Vector: CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

References

https://github.com/FlowiseAI/Flowise/security/advisories/GHSA-5xvg-pmgg-3mxr x_refsource_CONFIRM
https://github.com/FlowiseAI/Flowise/pull/6499 x_refsource_MISC
https://github.com/FlowiseAI/Flowise/commit/f4e2794f6a576b94578f2fdafbf49c2fb304626c x_refsource_MISC
https://github.com/FlowiseAI/Flowise/releases/tag/flowise@3.1.3 x_refsource_MISC