← Back to CVE Explorer

CVE-2026-44334

Full vulnerability record from the local CVENow database.

Description

PraisonAI is a multi-agent teams system. From version 4.5.139 to before version 4.6.32, CVE-2026-40287's fix gated tools.py auto-import behind PRAISONAI_ALLOW_LOCAL_TOOLS=true in two files (tool_resolver.py, api/call.py). A third import sink in praisonai/templates/tool_override.py was missed and remains unguarded. It is reached by the recipe runner on every recipe execution and is remotely triggerable through POST /v1/recipes/run with a recipe value pointing at any local absolute path or any GitHub repo (because SecurityConfig.allow_any_github defaults to True). The attacker drops a tools.py next to TEMPLATE.yaml; the server exec_module()s it. No auth required by default, no environment opt-in required. This issue has been patched in version 4.6.32.

Severity
HIGH
CVSS score
8.4 (v3.1)
Vulnerability status
Analyzed
Source identifier
Published
2026-05-08 14:16:46.143000
Last modified
2026-10-26 18:10:00.173000
View original CVE JSON
{
  "id": "CVE-2026-44334",
  "sourceIdentifier": "[email protected]",
  "published": "2026-05-08T14:16:46.143",
  "lastModified": "2026-10-26T18:10:00.173",
  "vulnStatus": "Analyzed",
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "PraisonAI is a multi-agent teams system. From version 4.5.139 to before version 4.6.32, CVE-2026-40287's fix gated tools.py auto-import behind PRAISONAI_ALLOW_LOCAL_TOOLS=true in two files (tool_resolver.py, api/call.py). A third import sink in praisonai/templates/tool_override.py was missed and remains unguarded. It is reached by the recipe runner on every recipe execution and is remotely triggerable through POST /v1/recipes/run with a recipe value pointing at any local absolute path or any GitHub repo (because SecurityConfig.allow_any_github defaults to True). The attacker drops a tools.py next to TEMPLATE.yaml; the server exec_module()s it. No auth required by default, no environment opt-in required. This issue has been patched in version 4.6.32."
    },
    {
      "lang": "es",
      "value": "PraisonAI es un sistema de equipos multiagente. Desde la versión 4.5.139 hasta antes de la versión 4.6.32, la corrección de CVE-2026-40287 restringió la autoimportación de tools.py detrás de PRAISONAI_ALLOW_LOCAL_TOOLS=true en dos archivos (tool_resolver.py, API/call.py). Un tercer punto de importación en praisonai/templates/tool_override.py fue pasado por alto y permanece sin protección. Es alcanzado por el ejecutor de recetas en cada ejecución de receta y es activable remotamente a través de POST /v1/recipes/run con un valor de receta que apunta a cualquier ruta absoluta local o a cualquier repositorio de GitHub (porque SecurityConfig.allow_any_github por defecto es True). El atacante deja caer un tools.py junto a TEMPLATE.yaml; el servidor lo exec_module(). No se requiere autenticación por defecto, no se requiere una opción de participación en el entorno. Este problema ha sido parcheado en la versión 4.6.32."
    }
  ],
  "affected": [
    {
      "source": "[email protected]",
      "affectedData": [
        {
          "vendor": "MervinPraison",
          "product": "PraisonAI",
          "versions": [
            {
              "version": ">= 4.5.139, < 4.6.32",
              "status": "affected"
            }
          ]
        }
      ]
    }
  ],
  "metrics": {
    "cvssMetricV31": [
      {
        "source": "[email protected]",
        "type": "Secondary",
        "cvssData": {
          "version": "3.1",
          "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
          "baseScore": 8.4,
          "baseSeverity": "HIGH",
          "attackVector": "LOCAL",
          "attackComplexity": "LOW",
          "privilegesRequired": "NONE",
          "userInteraction": "NONE",
          "scope": "UNCHANGED",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "availabilityImpact": "HIGH"
        },
        "exploitabilityScore": 2.5,
        "impactScore": 5.9
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "timestamp": "2026-05-08T23:20:04.614320Z",
          "id": "CVE-2026-44334",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "version": "2.0.3"
        }
      }
    ]
  },
  "weaknesses": [
    {
      "source": "[email protected]",
      "type": "Secondary",
      "description": [
        {
          "lang": "en",
          "value": "CWE-94"
        }
      ]
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "operator": "OR",
          "negate": false,
          "cpeMatch": [
            {
              "vulnerable": true,
              "criteria": "cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*",
              "versionStartIncluding": "4.5.139",
              "versionEndExcluding": "4.6.32",
              "matchCriteriaId": "FB26C0F1-7FD0-40F7-9942-731772F9ECAE"
            }
          ]
        }
      ]
    }
  ],
  "references": [
    {
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xcmw-grxf-wjhj",
      "source": "[email protected]",
      "tags": [
        "Exploit",
        "Vendor Advisory"
      ]
    }
  ]
}