CVE-2026-9196

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.

CVSS v3 8.1 HIGH

8.1^/10

CVSS v3 : HIGH

Vector :

Exploitability : 2.8 / Impact : 5.2

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required LOW

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact NONE

Scope UNCHANGED

References

Link	Resource
https://www.ibm.com/support/pages/node/7282646	Vendor Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:langflow:langflow:*:*:*:*:*:*:*:*

History

23 Oct 2026, 21:10

Type	Values Removed	Values Added
Summary		(es) IBM Langflow OSS 1.0.0 hasta 1.10.3 podría permitir a un atacante autenticado ejecutar código no intencionado durante la validación del Asistente Agéntico debido a un manejo inadecuado de los componentes generados por LLM. La aplicación ejecuta código Python generado por el modelo en el backend durante la validación antes de la aprobación del usuario, lo que podría permitir a un atacante desencadenar efectos secundarios como acceso a la red saliente, interacción con el sistema de archivos o exfiltración de datos con los privilegios del proceso de backend de Langflow.

Information

Published : 2026-08-05 19:17

Updated : 2026-10-24 13:10

NVD link : CVE-2026-9196

Mitre link : CVE-2026-9196

CVE.ORG link : CVE-2026-9196

JSON object : View

Products Affected

langflow

langflow

CWE

CWE-94

Improper Control of Generation of Code ('Code Injection')

{"id": "CVE-2026-9196", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-9196", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-08-06T03:55:57.821807Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "psirt@us.ibm.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 8.1, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 5.2, "exploitabilityScore": 2.8}, {"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 8.8, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "LOW", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 2.8}]}, "affected": [{"source": "psirt@us.ibm.com", "affectedData": [{"cpes": ["cpe:2.3:a:ibm:langflow_oss:1.0.0:*:*:*:*:*:*:*", "cpe:2.3:a:ibm:langflow_oss:1.10.3:*:*:*:*:*:*:*"], "vendor": "IBM", "product": "Langflow OSS", "versions": [{"status": "affected", "version": "1.0.0", "versionType": "semver", "lessThanOrEqual": "1.10.3"}]}]}], "published": "2026-08-05T19:17:48.523", "references": [{"url": "https://www.ibm.com/support/pages/node/7282646", "tags": ["Vendor Advisory"], "source": "psirt@us.ibm.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "psirt@us.ibm.com", "description": [{"lang": "en", "value": "CWE-94"}]}], "descriptions": [{"lang": "en", "value": "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\u2011generated components. The application executes model\u2011generated 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."}, {"lang": "es", "value": "IBM Langflow OSS 1.0.0 hasta 1.10.3 podr\u00eda permitir a un atacante autenticado ejecutar c\u00f3digo no intencionado durante la validaci\u00f3n del Asistente Ag\u00e9ntico debido a un manejo inadecuado de los componentes generados por LLM. La aplicaci\u00f3n ejecuta c\u00f3digo Python generado por el modelo en el backend durante la validaci\u00f3n antes de la aprobaci\u00f3n del usuario, lo que podr\u00eda permitir a un atacante desencadenar efectos secundarios como acceso a la red saliente, interacci\u00f3n con el sistema de archivos o exfiltraci\u00f3n de datos con los privilegios del proceso de backend de Langflow."}], "lastModified": "2026-10-24T13:10:00.147", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:langflow:langflow:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "9D820E7E-FD86-4EE6-9F29-E8DF9EC23F30", "versionEndExcluding": "1.11.0", "versionStartIncluding": "1.0.0"}], "operator": "OR"}]}], "sourceIdentifier": "psirt@us.ibm.com"}