« Volver al listado

CVE-2026-47395

Estado: AplazadaMedia (5.5)—

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:<http-or-https-url>`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context.

Leer descripción completaMostrar menos

There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator's machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix.

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).

Tecnologías afectadas (2)

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

Praison — PraisonaiAIPraison — PraisonaiagentsAI

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2026-47395",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-47395",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-07-21T17:09:32.354388Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 5.5,
          "attackVector": "LOCAL",
          "baseSeverity": "MEDIUM",
          "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N",
          "integrityImpact": "NONE",
          "userInteraction": "REQUIRED",
          "attackComplexity": "LOW",
          "availabilityImpact": "NONE",
          "privilegesRequired": "NONE",
          "confidentialityImpact": "HIGH"
        },
        "impactScore": 3.6,
        "exploitabilityScore": 1.8
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "MervinPraison",
          "product": "PraisonAI",
          "versions": [
            {
              "status": "affected",
              "version": "< 4.6.40"
            }
          ]
        },
        {
          "vendor": "MervinPraison",
          "product": "praisonaiagents",
          "versions": [
            {
              "status": "affected",
              "version": "< 1.6.40"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-07-21T16:17:12.600",
  "references": [
    {
      "url": "https://github.com/MervinPraison/PraisonAI/commit/b0d8f777528f3253a0cfb0a3ef65455da6ae32f6",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/MervinPraison/PraisonAI/pull/1684",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-5cxw-77wg-jrf3",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ],
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-200"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:<http-or-https-url>`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response body is prepended to the final model prompt context. There is no loopback/private-address restriction, no metadata-service restriction, and no approval gate before the fetch. As a result, attacker-influenced prompt text can cause the operator's machine to fetch localhost-only HTTP resources and inject the response into model context. PraisonAI version 4.6.40 and praisonaiagents version 1.6.40 contain a fix."
    }
  ],
  "lastModified": "2026-07-21T18:59:43.940",
  "sourceIdentifier": "security-advisories@github.com"
}