FKIE_CVE-2024-5826

Vulnerability from fkie_nvd - Published: 2024-06-27 19:15 - Updated: 2026-06-17 08:16
Severity
9.8 (Critical) - CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Summary
In the latest version of vanna-ai/vanna, the `vanna.ask` function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the `exec` function in `src/vanna/base/base.py`. This vulnerability can be exploited by an attacker to achieve remote code execution on the app backend server, potentially gaining full control of the server.
References
security@huntr.devhttps://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369
af854a3a-2127-422b-91ae-364da2661108https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369
Impacted products
Vendor Product Version
To clipboard 

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "vanna-ai/vanna",
          "vendor": "vanna-ai",
          "versions": [
            {
              "lessThanOrEqual": "latest",
              "status": "affected",
              "version": "unspecified",
              "versionType": "custom"
            }
          ]
        }
      ],
      "source": "security@huntr.dev"
    },
    {
      "affectedData": [
        {
          "cpes": [
            "cpe:2.3:a:vanna-ai:vanna:-:*:*:*:*:*:*:*"
          ],
          "defaultStatus": "unknown",
          "product": "vanna",
          "vendor": "vanna-ai",
          "versions": [
            {
              "status": "affected",
              "version": "0"
            }
          ]
        }
      ],
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "In the latest version of vanna-ai/vanna, the `vanna.ask` function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the `exec` function in `src/vanna/base/base.py`. This vulnerability can be exploited by an attacker to achieve remote code execution on the app backend server, potentially gaining full control of the server."
    },
    {
      "lang": "es",
      "value": "En la \u00faltima versi\u00f3n de vanna-ai/vanna, la funci\u00f3n `vanna.ask` es vulnerable a la ejecuci\u00f3n remota de c\u00f3digo debido a la inyecci\u00f3n r\u00e1pida. La causa principal es la falta de una zona de pruebas al ejecutar c\u00f3digo generado por LLM, lo que permite a un atacante manipular el c\u00f3digo ejecutado por la funci\u00f3n `exec` en `src/vanna/base/base.py`. Un atacante puede aprovechar esta vulnerabilidad para lograr la ejecuci\u00f3n remota de c\u00f3digo en el servidor backend de la aplicaci\u00f3n, obteniendo potencialmente el control total del servidor."
    }
  ],
  "id": "CVE-2024-5826",
  "lastModified": "2026-06-17T08:16:43.470",
  "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": "security@huntr.dev",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2024-5826",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2024-06-28T15:19:12.368194Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2024-06-27T19:15:17.350",
  "references": [
    {
      "source": "security@huntr.dev",
      "url": "https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369"
    },
    {
      "source": "af854a3a-2127-422b-91ae-364da2661108",
      "url": "https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369"
    }
  ],
  "sourceIdentifier": "security@huntr.dev",
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-94"
        }
      ],
      "source": "security@huntr.dev",
      "type": "Secondary"
    }
  ]
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

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.


Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.