CVE-2026-33873 Langflow has Authenticated Code Execution in Agentic Assistant Validation
Authenticated attackers can execute arbitrary Python code on the server by influencing LLM output in the Agentic Assistant validation phase.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-33873?
CVE-2026-33873 is a critical code injection vulnerability in Langflow Langflow, published on 27 Mar 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.9.0, the Agentic Assistant feature in Langflow executes LLM-generated Python code during its validation phase. Although this phase appears intended to validate generated component code, the implementation reaches dynamic execution sinks and instantiates the generated class server-side. In deployments where an attacker can access the Agentic Assistant feature and influence the model output, this can result in arbitrary server-side Python execution. Version 1.9.0 fixes the issue.
Weakness: CWE-94
Which versions are affected by CVE-2026-33873?
3 open source packages ship an affected version, including langflow. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
langflow PyPI | All versions | 1.9.0 |
langflow PyPI | All versions | 1.9.0 |
langflow PyPI | All versions | 1.9.0 |
Products include Langflow Langflow.
How do I fix CVE-2026-33873?
Upgrade langflow to 1.9.0 or later.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-33873 being exploited?
There is no known exploitation of CVE-2026-33873 in the wild and no public exploit code.
Other vulnerabilities in Langflow Langflow
Sources
Also known as ECHO-e568-958c-ec51, GHSA-v8hw-mh8c-jxfc, PYSEC-2026-82.