« Volver al listado

CVE-2026-47391

Estado: AplazadaCrítica (9.8)—

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool.

Leer descripción completaMostrar menos

In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches 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.

Endpoint JSON-RPC sin autenticación en red pública (AV:N, PR:N, UI:N) permite ejecución arbitraria de Python mediante eval() en herramienta calculate; acceso a historial de tareas y APIs de cancelación amplía confidencialidad e integridad.

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 ContentRestrict File and Directory PermissionsRemote Data StorageNetwork Segmentation

Tecnologías afectadas (1)

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

Praison — PraisonaiAI

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2026-47391",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-47391",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-07-23T14:27:02.928342Z"
        }
      }
    ],
    "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": "MervinPraison",
          "product": "PraisonAI",
          "versions": [
            {
              "status": "affected",
              "version": "< 4.6.40"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-07-21T16:17:11.920",
  "references": [
    {
      "url": "https://github.com/MervinPraison/PraisonAI/commit/e0fb8e7dd1ee6759c18ed07f436c21dbd9c20747",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/MervinPraison/PraisonAI/pull/1793",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg22-4gmj-prxw",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ],
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-95"
        },
        {
          "lang": "en",
          "value": "CWE-306"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue."
    }
  ],
  "lastModified": "2026-07-23T15:17:11.303",
  "sourceIdentifier": "security-advisories@github.com"
}