Langflow: IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute…
Langflow
More for Langflow RSS feed for Langflow
- Severity
- High, CVSS 8.8
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- Record
- CVE-2026-9196
- Affects
- Langflow
- Known exploited
- Not listed in the CISA Known Exploited Vulnerabilities catalog
- Published
- Record first published by the source
- August 5, 2026
- Source last modified
- October 24, 2026
Description
IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components. The application executes model‑generated Python code in the backend during validation prior to user approval, which may allow an attacker to trigger side effects such as outbound network access, file system interaction, or data exfiltration with the privileges of the Langflow backend process.
Description quoted from the NVD record.
Who is affected
Langflow (also called IBM Langflow OSS) is a tool for building apps that use AI language models. This flaw affects versions 1.0.0 through 1.10.3. It is in the Agentic Assistant feature. When the assistant checks a building block written by the AI model, Langflow runs that code on its server before anyone approves it. Someone with a login to your Langflow could use this to run unintended code. That code could contact other computers over the network, work with files on the server, or send data out, with the same access as Langflow itself. This flaw is rated High.
What to do
- The person who installed or runs Langflow for your organization should check which version you are using. This flaw affects versions 1.0.0 through 1.10.3.
- No fixed version is named for this flaw yet, so check the vendor advisory linked on this page for a fixed release. When one is available, install it as soon as you can.
- If an IT provider or vendor runs Langflow for your organization, send them this advisory and ask when the update will be done.
Analysis written from the source record as of October 24, 2026 and reviewed before publishing.