CVE-2026-33873

Source
https://cve.org/CVERecord?id=CVE-2026-33873
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-33873.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2026-33873
Aliases
Downstream
Published
2026-03-27T20:04:23.646Z
Modified
2026-05-20T08:11:35.637070656Z
Severity
  • 9.3 (Critical) CVSS_V4 - 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 CVSS Calculator
Summary
Langflow has Authenticated Code Execution in Agentic Assistant Validation
Details

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.

Database specific
{
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/33xxx/CVE-2026-33873.json",
    "cna_assigner": "GitHub_M",
    "cwe_ids": [
        "CWE-94"
    ]
}
References

Affected packages

Git / github.com/langflow-ai/langflow

Affected ranges

Type
GIT
Repo
https://github.com/langflow-ai/langflow
Events
Introduced
0 Unknown introduced commit / All previous commits are affected
Fixed
Database specific
{
    "versions": [
        {
            "introduced": "0"
        },
        {
            "fixed": "1.9.0"
        }
    ]
}

Database specific

source
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2026-33873.json"