FKIE_CVE-2026-0761

Vulnerability from fkie_nvd - Published: 2026-01-23 04:16 - Updated: 2026-02-20 13:41
Severity ?
9.8 (Critical) - CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Summary
Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT. Authentication is not required to exploit this vulnerability. The specific flaw exists within the actionoutput_str_to_mapping function. The issue results from the lack of proper validation of a user-supplied string before using it to execute Python code. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-28124.
References
zdi-disclosures@trendmicro.comhttps://www.zerodayinitiative.com/advisories/ZDI-26-027/Third Party Advisory
Impacted products
Vendor Product Version
deepwisdom metagpt 0.8.1
To clipboard 

{
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:deepwisdom:metagpt:0.8.1:*:*:*:*:*:*:*",
              "matchCriteriaId": "F3E5C450-428D-4576-BCB3-622B8633EF67",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "Foundation Agents MetaGPT actionoutput_str_to_mapping Code Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Foundation Agents MetaGPT. Authentication is not required to exploit this vulnerability.\n\nThe specific flaw exists within the actionoutput_str_to_mapping function. The issue results from the lack of proper validation of a user-supplied string before using it to execute Python code. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-28124."
    },
    {
      "lang": "es",
      "value": "Vulnerabilidad de inyecci\u00f3n de c\u00f3digo de ejecuci\u00f3n remota de c\u00f3digo en Foundation Agents MetaGPT actionoutput_str_to_mapping. Esta vulnerabilidad permite a atacantes remotos ejecutar c\u00f3digo arbitrario en instalaciones afectadas de Foundation Agents MetaGPT. No se requiere autenticaci\u00f3n para explotar esta vulnerabilidad.\n\nLa falla espec\u00edfica reside en la funci\u00f3n actionoutput_str_to_mapping. El problema se debe a la falta de validaci\u00f3n adecuada de una cadena proporcionada por el usuario antes de usarla para ejecutar c\u00f3digo Python. Un atacante puede aprovechar esta vulnerabilidad para ejecutar c\u00f3digo en el contexto de la cuenta de servicio. Fue ZDI-CAN-28124."
    }
  ],
  "id": "CVE-2026-0761",
  "lastModified": "2026-02-20T13:41:55.697",
  "metrics": {
    "cvssMetricV30": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 9.8,
          "baseSeverity": "CRITICAL",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
          "version": "3.0"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 5.9,
        "source": "zdi-disclosures@trendmicro.com",
        "type": "Secondary"
      }
    ]
  },
  "published": "2026-01-23T04:16:02.847",
  "references": [
    {
      "source": "zdi-disclosures@trendmicro.com",
      "tags": [
        "Third Party Advisory"
      ],
      "url": "https://www.zerodayinitiative.com/advisories/ZDI-26-027/"
    }
  ],
  "sourceIdentifier": "zdi-disclosures@trendmicro.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-94"
        }
      ],
      "source": "zdi-disclosures@trendmicro.com",
      "type": "Primary"
    }
  ]
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.



Detection rules are retrieved from Rulezet.