« Volver al listado

CVE-2026-107287

Estado: AnalizadaMedia (6.5)—

Pydantic AI es un framework de agentes en Python para crear aplicaciones y flujos de trabajo con IA generativa. Desde la 1.77.0 hasta la 1.107.7 y la 2.52.0, web_fetch_tool local y la alternativa local de WebFetch pueden consumir una cantidad excesiva de CPU y memoria durante la conversión de HTML a Markdown de HTML controlado por el atacante que contenga elementos de bloque profundamente anidados.

Leer descripción completaMostrar menos

La conversión vuelve a procesar repetidamente el texto acumulado y puede ampliar considerablemente la salida intermedia antes de que se aplique el límite de contenido devuelto, lo que permite que una obtención dirigida por el modelo retrase otros trabajos del proceso. La obtención web nativa del proveedor no está afectada. Este problema está corregido en las versiones 1.107.7 y 2.52.0.

Traducción automática del texto original de NVD (en inglés).

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.

El vector CVSS:3.1 con UI:R (requiere interacción del usuario) y AV:N (red) indica ejecución en cliente. La descripción explícita de consumo excesivo de CPU/memoria en procesamiento de HTML controlado por atacante mediante web_fetch_tool sustenta DoS (T1499).

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

Filter Network TrafficApplication Isolation and SandboxingExploit ProtectionUpdate Software

Tecnologías afectadas (1)

Pydantic — Pydantic AI

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2026-107287",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-107287",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-10-14T00:58:47.200664Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 6.5,
          "attackVector": "NETWORK",
          "baseSeverity": "MEDIUM",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H",
          "integrityImpact": "NONE",
          "userInteraction": "REQUIRED",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "confidentialityImpact": "NONE"
        },
        "impactScore": 3.6,
        "exploitabilityScore": 2.8
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "pydantic",
          "product": "pydantic-ai",
          "versions": [
            {
              "status": "affected",
              "version": ">= 1.77.0, < 1.107.7"
            },
            {
              "status": "affected",
              "version": ">= 2.0.0b1, < 2.52.0"
            }
          ]
        },
        {
          "vendor": "pydantic",
          "product": "pydantic-ai-slim",
          "versions": [
            {
              "status": "affected",
              "version": ">= 1.77.0, < 1.107.7"
            },
            {
              "status": "affected",
              "version": ">= 2.0.0b1, < 2.52.0"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-10-08T16:17:03.973",
  "references": [
    {
      "url": "https://github.com/pydantic/pydantic-ai/commit/2b247add4950bef61d352e7ca8aefbd20539180c",
      "tags": [
        "Patch"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/pydantic/pydantic-ai/commit/2fd38792693da00a3ca5412aeffb436787af3545",
      "tags": [
        "Patch"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/pydantic/pydantic-ai/pull/8984",
      "tags": [
        "Patch",
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/pydantic/pydantic-ai/pull/8985",
      "tags": [
        "Patch",
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.7",
      "tags": [
        "Patch",
        "Release Notes",
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.52.0",
      "tags": [
        "Patch",
        "Release Notes",
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-v36g-jcw9-x7cw",
      "tags": [
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-400"
        },
        {
          "lang": "en",
          "value": "CWE-407"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.7 and 2.52.0, the local web_fetch_tool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML containing deeply nested block elements. Conversion repeatedly reprocesses accumulated text and can greatly expand intermediate output before the returned-content limit is applied, allowing a model-directed fetch to delay other work in the process. Provider-native web fetching is not affected. This issue is fixed in versions 1.107.7 and 2.52.0."
    }
  ],
  "lastModified": "2026-10-14T01:17:04.887",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:pydantic:pydantic_ai:*:*:*:*:*:python:*:*",
              "vulnerable": true,
              "matchCriteriaId": "FF3E6D2A-5751-433C-8415-AE070B5FFF87",
              "versionEndExcluding": "1.107.7",
              "versionStartIncluding": "1.77.0"
            },
            {
              "criteria": "cpe:2.3:a:pydantic:pydantic_ai:*:-:*:*:*:python:*:*",
              "vulnerable": true,
              "matchCriteriaId": "3385037B-7B85-456F-972A-205F60EB51A2",
              "versionEndExcluding": "2.52.0",
              "versionStartIncluding": "2.0.0"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "security-advisories@github.com"
}