FKIE_CVE-2024-7764

Vulnerability from fkie_nvd - Published: 2025-03-20 10:15 - Updated: 2025-03-20 10:15
Severity ?
8.1 (High) - CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
Summary
Vanna-ai v0.6.2 is vulnerable to SQL Injection due to insufficient protection against injecting additional SQL commands from user requests. The vulnerability occurs when the `generate_sql` function calls `extract_sql` with the LLM response. An attacker can include a semi-colon between a search data field and their own command, causing the `extract_sql` function to remove all LLM generated SQL and execute the attacker's command if it passes the `is_sql_valid` function. This allows the execution of user-defined SQL beyond the expected boundaries, notably the trained schema.
References
security@huntr.devhttps://huntr.com/bounties/85d403b1-fbed-42e9-9ec1-2f79abf6eb0f
Impacted products
Vendor Product Version
To clipboard 

{
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "Vanna-ai v0.6.2 is vulnerable to SQL Injection due to insufficient protection against injecting additional SQL commands from user requests. The vulnerability occurs when the `generate_sql` function calls `extract_sql` with the LLM response. An attacker can include a semi-colon between a search data field and their own command, causing the `extract_sql` function to remove all LLM generated SQL and execute the attacker\u0027s command if it passes the `is_sql_valid` function. This allows the execution of user-defined SQL beyond the expected boundaries, notably the trained schema."
    },
    {
      "lang": "es",
      "value": "Vanna-ai v0.6.2 es vulnerable a la inyecci\u00f3n de SQL debido a la protecci\u00f3n insuficiente contra la inyecci\u00f3n de comandos SQL adicionales provenientes de las solicitudes de usuario. La vulnerabilidad se produce cuando la funci\u00f3n `generate_sql` llama a `extract_sql` con la respuesta LLM. Un atacante puede incluir un punto y coma entre un campo de datos de b\u00fasqueda y su propio comando, lo que provoca que la funci\u00f3n `extract_sql` elimine todo el SQL generado por LLM y ejecute el comando del atacante si este pasa la funci\u00f3n `is_sql_valid`. Esto permite la ejecuci\u00f3n de SQL definido por el usuario m\u00e1s all\u00e1 de los l\u00edmites previstos, en particular del esquema entrenado."
    }
  ],
  "id": "CVE-2024-7764",
  "lastModified": "2025-03-20T10:15:36.717",
  "metrics": {
    "cvssMetricV30": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "NONE",
          "baseScore": 8.1,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N",
          "version": "3.0"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 5.2,
        "source": "security@huntr.dev",
        "type": "Secondary"
      }
    ]
  },
  "published": "2025-03-20T10:15:36.717",
  "references": [
    {
      "source": "security@huntr.dev",
      "url": "https://huntr.com/bounties/85d403b1-fbed-42e9-9ec1-2f79abf6eb0f"
    }
  ],
  "sourceIdentifier": "security@huntr.dev",
  "vulnStatus": "Awaiting Analysis",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-89"
        }
      ],
      "source": "security@huntr.dev",
      "type": "Secondary"
    }
  ]
}


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.