« Volver al listado

CVE-2026-27966

Estado: AnalizadaCrítica (9.8)—

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes `allow_dangerous_code=True`, which automatically exposes LangChain’s Python REPL tool (`python_repl_ast`). As a result, an attacker can execute arbitrary Python and OS commands on the server via prompt injection, leading to full Remote Code Execution (RCE). Version 1.8.0 fixes the issue.

CVSS

Probabilidad de explotación (EPSS)

EPSS (Exploit Prediction Scoring System, de FIRST) estima la probabilidad de que una vulnerabilidad sea explotada en 30 días. Complementa a CVSS (impacto) y a CISA KEV (explotación confirmada).

🎯 Técnicas ATT&CK

Cómo se explota esta vulnerabilidad y qué consigue el atacante, en el lenguaje de MITRE ATT&CK.

CVE crítica en aplicación expuesta (Langflow): inyección de prompt en CSV Agent permite ejecución arbitraria de Python y comandos OS. AV:N, PR:N, UI:N confirma T1190. T1059 por RCE explícita; T1578 por control potencial de recursos en servidor comprometido.

Inferido por nuestro agente de análisis a partir de la descripción oficial, el vector CVSS y la CWE, y comprobado por un supervisor. Puede contener errores.

🛡️ Mitigaciones ATT&CK que cubren estas técnicas

Privileged Account ManagementVulnerability ScanningRestrict Web-Based ContentNetwork SegmentationLimit Software InstallationLimit Access to Resource Over Network

Tecnologías afectadas (1)

Langflow — Langflow

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2026-27966",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-27966",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-02-26T00:00:00+00:00"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 9.8,
          "attackVector": "NETWORK",
          "baseSeverity": "CRITICAL",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
          "integrityImpact": "HIGH",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "confidentialityImpact": "HIGH"
        },
        "impactScore": 5.9,
        "exploitabilityScore": 3.9
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "langflow-ai",
          "product": "langflow",
          "versions": [
            {
              "status": "affected",
              "version": "< 1.8.0"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-02-26T02:16:23.833",
  "references": [
    {
      "url": "https://github.com/langflow-ai/langflow/commit/d8c6480daa17b2f2af0b5470cdf5c3d28dc9e508",
      "tags": [
        "Patch"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/langflow-ai/langflow/security/advisories/GHSA-3645-fxcv-hqr4",
      "tags": [
        "Exploit",
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-94"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to version 1.8.0, the CSV Agent node in Langflow hardcodes `allow_dangerous_code=True`, which automatically exposes LangChain’s Python REPL tool (`python_repl_ast`). As a result, an attacker can execute arbitrary Python and OS commands on the server via prompt injection, leading to full Remote Code Execution (RCE). Version 1.8.0 fixes the issue."
    },
    {
      "lang": "es",
      "value": "Langflow es una herramienta para construir y desplegar agentes y flujos de trabajo impulsados por IA. Antes de la versión 1.8.0, el nodo CSV Agent en Langflow codifica de forma rígida 'allow_dangerous_code=True', lo que expone automáticamente la herramienta Python REPL de LangChain ('python_repl_ast'). Como resultado, un atacante puede ejecutar comandos arbitrarios de Python y del sistema operativo en el servidor a través de inyección de prompts, lo que lleva a una ejecución remota de código (RCE) completa. La versión 1.8.0 soluciona el problema."
    }
  ],
  "lastModified": "2026-06-17T10:27:59.160",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:langflow:langflow:*:*:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "2F2C3DDC-4ECF-4814-AC58-D3D09E54D9B2",
              "versionEndExcluding": "1.8.0"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "security-advisories@github.com"
}