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

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

• Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
• EPSS 0.8%, percentile 57: FIRST’s model estimates a 0.8% chance of exploitation activity in the next 30 days, higher than 57% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
• Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
• Only applies if your dependency tree includes flowise (npm) <= 3.1.2, fixed in 3.1.3; flowise-components (npm) <= 3.1.2, fixed in 3.1.3. Check your lockfile, including transitive dependencies.

What it is

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 CSVAgents 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.

From the GitHub advisory

-- ABSTRACT -------------------------------------

Trend Micro's Zero Day Initiative has identified a vulnerability affecting the following products: Flowise - Flowise

-- VULNERABILITY DETAILS ------------------------ Version tested: 3.1.1 Installer file: https://github.com/FlowiseAI/Flowise (npm install flowise@3.1.1) Platform tested: Ubuntu 25.10

---

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. An attacker can leverage this to execute arbitrary code in the context of the user running the server.

Weakness type: CWE-94.

Product: flowise (npm) · Assigned by: GitHub_M · Published: 2026-08-04

Affected and fixed versions

Severity scores

• Attack vector: network (remotely reachable)
• Attack complexity: high (needs special conditions)
• Attack requirements: present (depends on deployment conditions)
• Privileges required: none (no login)
• User interaction: none

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

• CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
• CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
• FIRST EPSS (model of 2026-10-21): 0.81% probability of exploitation activity in the next 30 days; percentile 57.

Timeline

• 2026-08-04 — CVE record published by GitHub_M
• 2026-08-04 — GitHub-reviewed advisory GHSA-5xvg-pmgg-3mxr published (critical)
• 2026-08-05 — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

1. GitHub Advisory GHSA-5xvg-pmgg-3mxr github.com
2. CVE.org record CVE-2026-70477 cve.org
3. NVD entry CVE-2026-70477 nvd.nist.gov

Other references from the CVE record and advisory

1. github.com github.com
2. github.com github.com
3. github.com github.com
4. github.com github.com

Critical npm advisories · Today’s Security Digest