« Volver al listado

CVE-2025-34072

Estado: AplazadaCrítica (9.3)—

A data exfiltration vulnerability exists in Anthropic’s deprecated Slack Model Context Protocol (MCP) Server via automatic link unfurling. When an AI agent using the Slack MCP Server processes untrusted data, it can be manipulated to generate messages containing attacker-crafted hyperlinks embedding sensitive data. Slack’s link preview bots (e.g., Slack-LinkExpanding, Slackbot, Slack-ImgProxy) will then issue outbound requests to the attacker-controlled URL, resulting in zero-click exfiltration of private data.

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.

Red sin privilegios (AV:N/PR:N) en servidor expuesto. Impactos: lectura de datos sensibles (VC:H, CWE-200) vía exfiltración a URL controlada por atacante.

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

Vulnerability ScanningRestrict Web-Based ContentPrivileged Account ManagementNetwork SegmentationLimit Access to Resource Over NetworkFilter Network Traffic

Tecnologías afectadas (1)

⚠ Inferidas por IA a partir de la descripción — NVD aún no ha analizado esta CVE; no son CPE verificados.

Anthropic — Slack Model Context Protocol ServerAI

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2025-34072",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2025-34072",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2025-07-02T20:29:08.961760Z"
        }
      }
    ],
    "cvssMetricV40": [
      {
        "type": "Secondary",
        "source": "disclosure@vulncheck.com",
        "cvssData": {
          "Safety": "NOT_DEFINED",
          "version": "4.0",
          "Recovery": "NOT_DEFINED",
          "baseScore": 9.3,
          "Automatable": "NOT_DEFINED",
          "attackVector": "NETWORK",
          "baseSeverity": "CRITICAL",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:H/SI:H/SA:H/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": "HIGH",
          "vulnIntegrityImpact": "NONE",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "subAvailabilityImpact": "HIGH",
          "vulnAvailabilityImpact": "NONE",
          "availabilityRequirement": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "subConfidentialityImpact": "HIGH",
          "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": "disclosure@vulncheck.com",
      "affectedData": [
        {
          "vendor": "Anthropic",
          "modules": [
            "Anthropic Slack MCP Server",
            "Message content (post/reply body)"
          ],
          "product": "Slack MCP Server",
          "versions": [
            {
              "status": "affected",
              "version": "0"
            }
          ],
          "defaultStatus": "unaffected"
        }
      ]
    }
  ],
  "published": "2025-07-02T14:15:24.817",
  "references": [
    {
      "url": "https://embracethered.com/blog/posts/2025/security-advisory-anthropic-slack-mcp-server-data-leakage/",
      "source": "disclosure@vulncheck.com"
    },
    {
      "url": "https://vulncheck.com/advisories/anthropic-slack-mcp-server-data-exfiltration",
      "source": "disclosure@vulncheck.com"
    }
  ],
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "disclosure@vulncheck.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-20"
        },
        {
          "lang": "en",
          "value": "CWE-200"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "A data exfiltration vulnerability exists in Anthropic’s deprecated Slack Model Context Protocol (MCP) Server via automatic link unfurling. When an AI agent using the Slack MCP Server processes untrusted data, it can be manipulated to generate messages containing attacker-crafted hyperlinks embedding sensitive data. Slack’s link preview bots (e.g., Slack-LinkExpanding, Slackbot, Slack-ImgProxy) will then issue outbound requests to the attacker-controlled URL, resulting in zero-click exfiltration of private data."
    },
    {
      "lang": "es",
      "value": "Existe una vulnerabilidad de exfiltración de datos en el servidor obsoleto del Protocolo de Contexto de Modelo (MCP) de Slack de Anthropic mediante el despliegue automático de enlaces. Cuando un agente de IA que utiliza el servidor MCP de Slack procesa datos no confiables, estos pueden manipularse para generar mensajes con hipervínculos manipulados por el atacante que integran datos confidenciales. Los bots de previsualización de enlaces de Slack (p. ej., Slack-LinkExpanding, Slackbot, Slack-ImgProxy) emiten solicitudes salientes a la URL controlada por el atacante, lo que resulta en la exfiltración de datos privados sin necesidad de hacer clic."
    }
  ],
  "lastModified": "2026-06-17T09:13:25.430",
  "sourceIdentifier": "disclosure@vulncheck.com"
}