Vulnerability details

CVE-2026-33873

langflow-ai langflow

Langflow has Authenticated Code Execution in Agentic Assistant Validation

CVSS 4.0
9.3Critical

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.

CVSS scores

ScoreVersionSourceVector
9.3Critical 4.0 CVEProject cvelistV5 (CNA) (GitHub_M) CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N

Affected products

VendorProductVersionsSource
langflow-ai langflow < 1.9.0 CVEProject cvelistV5 (CNA)

References and advisories

16
Kolun on Telegram @kolunsec Exploited CVEs, key news and a daily digest Alerts for this product's next CVEsFollow the product to get new vulnerabilities on Telegram.

Details

Published
2026-03-27
Last updated
2026-04-02
State
Published
Assigner (CNA)
GitHub_M

Exploit prediction (EPSS)

1.45%
Probability of exploitation in 30 days
73.5%
Percentile (among all CVEs)

SSVC assessment (CISA)

Automatable
No
Exploitation
None
Technical impact
Total

Weaknesses (CWE)

  • CWE-94
    Improper Control of Generation of Code ('Code Injection')