{"cve":"CVE-2026-33873","nvd":{"published":"2026-03-27T21:17:23.953","modified":"2026-06-17T10:38:14.430","status":"Analyzed","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_v4":{"vector":"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","score":9.3},"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H","score":9.9},"cwes":["CWE-94"],"references":["https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/api/router.py#L252-L297","https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/api/schemas.py#L20-L31","https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/helpers/code_extraction.py#L11-L53","https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/helpers/validation.py#L27-L47","https://github.com/langflow-ai/langflow/blob/f7f4d1e70ba5eecd18162ec96f3571c2cfbcd1fc/src/backend/base/langflow/agentic/services/assistant_service.py#L142-L156"],"products":["langflow:langflow"],"source":"nvd","synced_at":"2026-10-19T22:28:18.033120106+00:00"},"epss":{"cve":"CVE-2026-33873","score":0.01452,"percentile":0.73397,"date":"2026-11-01"},"kev":null,"osv":[{"id":"GHSA-v8hw-mh8c-jxfc","url":"https://osv.dev/vulnerability/GHSA-v8hw-mh8c-jxfc","summary":"Langflow has Authenticated Code Execution in Agentic Assistant Validation","modified":"2026-06-06T01:00:08.177275641Z","packages":[{"ecosystem":"PyPI","name":"langflow","purl":"pkg:pypi/langflow","ranges":["<1.9.0"],"fixed":["1.9.0"]}]},{"id":"PYSEC-2026-82","url":"https://osv.dev/vulnerability/PYSEC-2026-82","summary":"","modified":"2026-05-20T09:19:04.693650Z","packages":[{"ecosystem":"PyPI","name":"langflow","purl":"pkg:pypi/langflow","ranges":["<1.9.0"],"fixed":["1.9.0"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}