CriticalVulnerabilityLLM-specific

GHSA-5xvg-pmgg-3mxr: Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability

Source: GitHub Advisory(opens in a new tab)
Identifiers: CVE-2026-70477GHSA-5xvg-pmgg-3mxr
Published: August 4, 2026
Record updated: October 9, 2026

Affected: flowise-components <= 3.1.2
flowise <= 3.1.2
Fixed in: 3.1.3
flowise-components 3.1.3 released June 25, 2026, 40 days before disclosure
flowise 3.1.3 released June 25, 2026, 40 days before disclosure
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.8%

Summary

Flowise version 3.1.1 (tested on Ubuntu 25.10) contains a flaw in the run method of the CSV_Agents class, used by the CSV Agent node. Untrusted input is placed into an LLM prompt without adequate sanitization, so a prompt injection can make the LLM return a malicious Python script. That script passes a regex blocklist validator in packages/components/src/pythonCodeValidator.ts, which can be bypassed, and then runs in pyodide, which is not sandboxed from the host OS, giving code execution as the server's service account. Authentication is not required to exploit it.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

Patch available: Yes
EPSS: 0.8%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.
Disclosure date: August 4, 2026

Weaknesses and techniques

AI threat technique (MITRE ATLAS): AML.T0051
AML.T0054

Affected

Packages: flowise-components@<= 3.1.2 (fixed: 3.1.3)
flowise@<= 3.1.2 (fixed: 3.1.3)

Classification

Attack type: Prompt injection,
Jailbreak
Attack sophistication: Moderate
AI component targeted: Agent
Impact: Confidentiality,
Integrity,
Availability
Labels: security,
safety

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative.

Original source: https://github.com/advisories/GHSA-5xvg-pmgg-3mxr

First tracked: August 4, 2026 at 08:01 PM ET, from GitHub Advisory Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Affected packages in the Exposure Registry

Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.

flowisenpmLLM dependency since 2024-03-12
flowise-componentsnpmLLM dependency since 2023-04-10 · 1 tracked dependent

Topics

Prompt injection and jailbreaks

Summary

Mitigation

Affected packages in the Exposure Registry

Topics

Related items