← Back to CVE Explorer

CVE-2026-55524

Full vulnerability record from the local CVENow database.

Description

PraisonAI is a multi-agent teams system. In versions prior to 1.6.58, the web_crawl tool performs its SSRF check only on the initially supplied URL, allowing the protection to be bypassed so the tool connects to attacker-chosen internal destinations. The check resolves the hostname once with socket.gethostbyname and rejects private/loopback/link-local results, but then passes the URL to a fetcher using httpx.Client(follow_redirects=True) (or urllib.request.urlopen when httpx is absent, which also follows redirects) that re-resolves the hostname at connect time with no further validation. This validate-here/fetch-there gap is exploitable through both HTTP redirects and DNS rebinding. If an attacker can influence URLs passed to web_crawl(), directly or through an agent/tool workflow, they can cause the PraisonAI host to fetch loopback, private-network, or cloud metadata endpoints reachable from that host, with the response body returned in the web_crawl() result. This issue has been fixed in version 1.6.58.

Severity
HIGH
CVSS score
7.5 (v3.1)
Vulnerability status
Deferred
Source identifier
Published
2026-08-05 20:17:10.847000
Last modified
2026-10-24 16:10:00.153000
View original CVE JSON
{
  "id": "CVE-2026-55524",
  "sourceIdentifier": "[email protected]",
  "published": "2026-08-05T20:17:10.847",
  "lastModified": "2026-10-24T16:10:00.153",
  "vulnStatus": "Deferred",
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "PraisonAI is a multi-agent teams system. In versions prior to 1.6.58, the web_crawl tool performs its SSRF check only on the initially supplied URL, allowing the protection to be bypassed so the tool connects to attacker-chosen internal destinations. The check resolves the hostname once with socket.gethostbyname and rejects private/loopback/link-local results, but then passes the URL to a fetcher using httpx.Client(follow_redirects=True) (or urllib.request.urlopen when httpx is absent, which also follows redirects) that re-resolves the hostname at connect time with no further validation. This validate-here/fetch-there gap is exploitable through both HTTP redirects and DNS rebinding. If an attacker can influence URLs passed to web_crawl(), directly or through an agent/tool workflow, they can cause the PraisonAI host to fetch loopback, private-network, or cloud metadata endpoints reachable from that host, with the response body returned in the web_crawl() result. This issue has been fixed in version 1.6.58."
    },
    {
      "lang": "es",
      "value": "PraisonAI es un sistema de equipos multiagente. En versiones anteriores a la 1.6.58, la herramienta web_crawl realiza su verificación de SSRF solo en la URL suministrada inicialmente, permitiendo que la protección sea eludida para que la herramienta se conecte a destinos internos elegidos por el atacante. La verificación resuelve el nombre de host una vez con socket.gethostbyname y rechaza resultados privados/loopback/link-local, pero luego pasa la URL a un ’fetcher’ usando httpx.Client(follow_redirects=True) (o urllib.request.urlopen cuando httpx está ausente, que también sigue redirecciones) que vuelve a resolver el nombre de host en el momento de la conexión sin validación adicional. Esta brecha de validar aquí/obtener allá es explotable a través de redirecciones HTTP y DNS rebinding. Si un atacante puede influir en las URL pasadas a web_crawl(), directamente o a través de un flujo de trabajo de agente/herramienta, pueden hacer que el host de PraisonAI obtenga puntos finales de loopback, de red privada o de metadatos de la nube accesibles desde ese host, con el cuerpo de la respuesta devuelto en el resultado de web_crawl(). Este problema ha sido solucionado en la versión 1.6.58."
    }
  ],
  "affected": [
    {
      "source": "[email protected]",
      "affectedData": [
        {
          "vendor": "MervinPraison",
          "product": "PraisonAI",
          "versions": [
            {
              "version": "< 1.6.58",
              "status": "affected"
            }
          ]
        }
      ]
    }
  ],
  "metrics": {
    "cvssMetricV31": [
      {
        "source": "[email protected]",
        "type": "Secondary",
        "cvssData": {
          "version": "3.1",
          "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:L/A:N",
          "baseScore": 7.5,
          "baseSeverity": "HIGH",
          "attackVector": "NETWORK",
          "attackComplexity": "HIGH",
          "privilegesRequired": "NONE",
          "userInteraction": "NONE",
          "scope": "CHANGED",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "LOW",
          "availabilityImpact": "NONE"
        },
        "exploitabilityScore": 2.2,
        "impactScore": 4.7
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "timestamp": "2026-08-06T14:41:35.294289Z",
          "id": "CVE-2026-55524",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "role": "CISA Coordinator",
          "version": "2.0.3"
        }
      }
    ]
  },
  "weaknesses": [
    {
      "source": "[email protected]",
      "type": "Secondary",
      "description": [
        {
          "lang": "en",
          "value": "CWE-367"
        },
        {
          "lang": "en",
          "value": "CWE-918"
        }
      ]
    }
  ],
  "references": [
    {
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg6p-v9vm-6fgj",
      "source": "[email protected]"
    },
    {
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vg6p-v9vm-6fgj",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ]
}