CVE-2026-27001

Estado: AnalizadaAlta (8.6)—

OpenClaw is a personal AI assistant. Prior to version 2026.2.15, OpenClaw embedded the current working directory (workspace path) into the agent system prompt without sanitization. If an attacker can cause OpenClaw to run inside a directory whose name contains control/format characters (for example newlines or Unicode bidi/zero-width markers), those characters could break the prompt structure and inject attacker-controlled instructions. Starting in version 2026.2.15, the workspace path is sanitized before it is embedded into any LLM prompt output, stripping Unicode control/format characters and explicit line/paragraph separators. Workspace path resolution also applies the same sanitization as defense-in-depth.

CVSS

Versión: 4.0
Vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Puntuación base: 8.6

Probabilidad de explotación (EPSS)

Probabilidad de explotación en los próximos 30 días: 0.23%
Percentil entre todas las CVEs puntuadas: 13
Fecha de la puntuación: 6/10/2026

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.

ExplotaciónT1068 Exploitation for Privilege Escalationprivilege escalation75 %
Impacto principalT1059 Command and Scripting Interpreterexecution80 %

Acceso local sin interacción del usuario (AV:L/PR:N/UI:N) permite inyectar instrucciones en el prompt del agente IA mediante manipulación del nombre del directorio, logrando ejecución de comandos.

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

Execution Prevention Threat Intelligence Program Restrict Web-Based Content Privileged Account Management Limit Software Installation Behavior Prevention on Endpoint

Tecnologías afectadas (1)

Openclaw — Openclaw

CWE

CWE-77

Referencias

JSON original (NVD)

Mostrar

{
  "id": "CVE-2026-27001",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-27001",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-02-20T15:29:33.374427Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Primary",
        "source": "nvd@nist.gov",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 7.8,
          "attackVector": "LOCAL",
          "baseSeverity": "HIGH",
          "vectorString": "CVSS:3.1/AV:L/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": 1.8
      }
    ],
    "cvssMetricV40": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "Safety": "NOT_DEFINED",
          "version": "4.0",
          "Recovery": "NOT_DEFINED",
          "baseScore": 8.6,
          "Automatable": "NOT_DEFINED",
          "attackVector": "LOCAL",
          "baseSeverity": "HIGH",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
          "exploitMaturity": "NOT_DEFINED",
          "providerUrgency": "NOT_DEFINED",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "attackRequirements": "NONE",
          "privilegesRequired": "NONE",
          "subIntegrityImpact": "NONE",
          "vulnIntegrityImpact": "HIGH",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "subAvailabilityImpact": "NONE",
          "vulnAvailabilityImpact": "HIGH",
          "availabilityRequirement": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "subConfidentialityImpact": "NONE",
          "vulnConfidentialityImpact": "HIGH",
          "confidentialityRequirement": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "vulnerabilityResponseEffort": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED"
        }
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "openclaw",
          "product": "openclaw",
          "versions": [
            {
              "status": "affected",
              "version": "< 2026.2.15"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-02-20T00:16:16.653",
  "references": [
    {
      "url": "https://github.com/openclaw/openclaw/commit/6254e96acf16e70ceccc8f9b2abecee44d606f79",
      "tags": [
        "Patch"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/openclaw/openclaw/releases/tag/v2026.2.15",
      "tags": [
        "Product",
        "Release Notes"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/openclaw/openclaw/security/advisories/GHSA-2qj5-gwg2-xwc4",
      "tags": [
        "Patch",
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-77"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "OpenClaw is a personal AI assistant. Prior to version 2026.2.15, OpenClaw embedded the current working directory (workspace path) into the agent system prompt without sanitization. If an attacker can cause OpenClaw to run inside a directory whose name contains control/format characters (for example newlines or Unicode bidi/zero-width markers), those characters could break the prompt structure and inject attacker-controlled instructions. Starting in version 2026.2.15, the workspace path is sanitized before it is embedded into any LLM prompt output, stripping Unicode control/format characters and explicit line/paragraph separators. Workspace path resolution also applies the same sanitization as defense-in-depth."
    },
    {
      "lang": "es",
      "value": "OpenClaw es un asistente personal de IA. Antes de la versión 2026.2.15, OpenClaw incrustaba el directorio de trabajo actual (ruta del espacio de trabajo) en el prompt del sistema del agente sin saneamiento. Si un atacante puede hacer que OpenClaw se ejecute dentro de un directorio cuyo nombre contiene caracteres de control/formato (por ejemplo, saltos de línea o marcadores Unicode bidireccionales/de ancho cero), esos caracteres podrían romper la estructura del prompt e inyectar instrucciones controladas por el atacante. A partir de la versión 2026.2.15, la ruta del espacio de trabajo se sanea antes de incrustarse en cualquier salida de prompt de LLM, eliminando caracteres de control/formato Unicode y separadores explícitos de línea/párrafo. La resolución de la ruta del espacio de trabajo también aplica el mismo saneamiento como defensa en profundidad."
    }
  ],
  "lastModified": "2026-06-17T10:26:30.990",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:openclaw:openclaw:*:*:*:*:*:node.js:*:*",
              "vulnerable": true,
              "matchCriteriaId": "3CD9AC99-DDDF-4177-9253-04A63CA027DC",
              "versionEndExcluding": "2026.2.15"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "security-advisories@github.com"
}