CVE-2024-7764 (GCVE-0-2024-7764)

Vulnerability from cvelistv5 – Published: 2025-03-20 10:11 – Updated: 2025-03-20 13:43
VLAI?
Title
SQL Injection in vanna-ai/vanna
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.
Severity ?
8.1 (High)
CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N
CWE
  • CWE-89 - Improper Neutralization of Special Elements used in an SQL Command
Assigner
References
Impacted products
Vendor Product Version
vanna-ai vanna-ai/vanna Affected: unspecified , ≤ latest (custom)
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2024-7764",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-03-20T13:43:19.044296Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-03-20T13:43:43.656Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vanna-ai/vanna",
          "vendor": "vanna-ai",
          "versions": [
            {
              "lessThanOrEqual": "latest",
              "status": "affected",
              "version": "unspecified",
              "versionType": "custom"
            }
          ]
        }
      ],
      "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."
        }
      ],
      "metrics": [
        {
          "cvssV3_0": {
            "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"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-89",
              "description": "CWE-89 Improper Neutralization of Special Elements used in an SQL Command",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-03-20T10:11:35.662Z",
        "orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
        "shortName": "@huntr_ai"
      },
      "references": [
        {
          "url": "https://huntr.com/bounties/85d403b1-fbed-42e9-9ec1-2f79abf6eb0f"
        }
      ],
      "source": {
        "advisory": "85d403b1-fbed-42e9-9ec1-2f79abf6eb0f",
        "discovery": "EXTERNAL"
      },
      "title": "SQL Injection in vanna-ai/vanna"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
    "assignerShortName": "@huntr_ai",
    "cveId": "CVE-2024-7764",
    "datePublished": "2025-03-20T10:11:35.662Z",
    "dateReserved": "2024-08-13T18:24:14.074Z",
    "dateUpdated": "2025-03-20T13:43:43.656Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1",
  "vulnerability-lookup:meta": {
    "nvd": "{\"cve\":{\"id\":\"CVE-2024-7764\",\"sourceIdentifier\":\"security@huntr.dev\",\"published\":\"2025-03-20T10:15:36.717\",\"lastModified\":\"2025-03-20T10:15:36.717\",\"vulnStatus\":\"Awaiting Analysis\",\"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.\"}],\"metrics\":{\"cvssMetricV30\":[{\"source\":\"security@huntr.dev\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.0\",\"vectorString\":\"CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N\",\"baseScore\":8.1,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.8,\"impactScore\":5.2}]},\"weaknesses\":[{\"source\":\"security@huntr.dev\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-89\"}]}],\"references\":[{\"url\":\"https://huntr.com/bounties/85d403b1-fbed-42e9-9ec1-2f79abf6eb0f\",\"source\":\"security@huntr.dev\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2024-7764\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2025-03-20T13:43:19.044296Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2025-03-20T13:43:40.306Z\"}}], \"cna\": {\"title\": \"SQL Injection in vanna-ai/vanna\", \"source\": {\"advisory\": \"85d403b1-fbed-42e9-9ec1-2f79abf6eb0f\", \"discovery\": \"EXTERNAL\"}, \"metrics\": [{\"cvssV3_0\": {\"scope\": \"UNCHANGED\", \"version\": \"3.0\", \"baseScore\": 8.1, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"vanna-ai\", \"product\": \"vanna-ai/vanna\", \"versions\": [{\"status\": \"affected\", \"version\": \"unspecified\", \"versionType\": \"custom\", \"lessThanOrEqual\": \"latest\"}]}], \"references\": [{\"url\": \"https://huntr.com/bounties/85d403b1-fbed-42e9-9ec1-2f79abf6eb0f\"}], \"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.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-89\", \"description\": \"CWE-89 Improper Neutralization of Special Elements used in an SQL Command\"}]}], \"providerMetadata\": {\"orgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"shortName\": \"@huntr_ai\", \"dateUpdated\": \"2025-03-20T10:11:35.662Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2024-7764\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2025-03-20T13:43:43.656Z\", \"dateReserved\": \"2024-08-13T18:24:14.074Z\", \"assignerOrgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"datePublished\": \"2025-03-20T10:11:35.662Z\", \"assignerShortName\": \"@huntr_ai\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.1"
    }
  }
}


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.