CVE-2024-5826 (GCVE-0-2024-5826)

Vulnerability from cvelistv5 – Published: 2024-06-27 18:40 – Updated: 2025-10-15 12:50
VLAI?
Title
Remote Code Execution via Prompt Injection in vanna-ai/vanna
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.
Severity ?
9.8 (Critical)
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CWE
  • CWE-94 - Improper Control of Generation of Code
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": [
      {
        "affected": [
          {
            "cpes": [
              "cpe:2.3:a:vanna-ai:vanna:-:*:*:*:*:*:*:*"
            ],
            "defaultStatus": "unknown",
            "product": "vanna",
            "vendor": "vanna-ai",
            "versions": [
              {
                "status": "affected",
                "version": "0"
              }
            ]
          }
        ],
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2024-5826",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2024-06-28T15:19:12.368194Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2024-06-28T15:26:27.620Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      },
      {
        "providerMetadata": {
          "dateUpdated": "2024-08-01T21:25:02.677Z",
          "orgId": "af854a3a-2127-422b-91ae-364da2661108",
          "shortName": "CVE"
        },
        "references": [
          {
            "tags": [
              "x_transferred"
            ],
            "url": "https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369"
          }
        ],
        "title": "CVE Program Container"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vanna-ai/vanna",
          "vendor": "vanna-ai",
          "versions": [
            {
              "lessThanOrEqual": "latest",
              "status": "affected",
              "version": "unspecified",
              "versionType": "custom"
            }
          ]
        }
      ],
      "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."
        }
      ],
      "metrics": [
        {
          "cvssV3_0": {
            "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"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94 Improper Control of Generation of Code",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-10-15T12:50:29.876Z",
        "orgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
        "shortName": "@huntr_ai"
      },
      "references": [
        {
          "url": "https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369"
        }
      ],
      "source": {
        "advisory": "90620087-44ac-4e43-b659-3c5d30889369",
        "discovery": "EXTERNAL"
      },
      "title": "Remote Code Execution via Prompt Injection in vanna-ai/vanna"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a",
    "assignerShortName": "@huntr_ai",
    "cveId": "CVE-2024-5826",
    "datePublished": "2024-06-27T18:40:37.441Z",
    "dateReserved": "2024-06-10T22:43:12.603Z",
    "dateUpdated": "2025-10-15T12:50:29.876Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1",
  "vulnerability-lookup:meta": {
    "fkie_nvd": {
      "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": "2024-11-21T09:48:24.490",
      "metrics": "{\"cvssMetricV30\": [{\"source\": \"security@huntr.dev\", \"type\": \"Secondary\", \"cvssData\": {\"version\": \"3.0\", \"vectorString\": \"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\", \"baseScore\": 9.8, \"baseSeverity\": \"CRITICAL\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"LOW\", \"privilegesRequired\": \"NONE\", \"userInteraction\": \"NONE\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"HIGH\", \"integrityImpact\": \"HIGH\", \"availabilityImpact\": \"HIGH\"}, \"exploitabilityScore\": 3.9, \"impactScore\": 5.9}]}",
      "published": "2024-06-27T19:15:17.350",
      "references": "[{\"url\": \"https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369\", \"source\": \"security@huntr.dev\"}, {\"url\": \"https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369\", \"source\": \"af854a3a-2127-422b-91ae-364da2661108\"}]",
      "sourceIdentifier": "security@huntr.dev",
      "vulnStatus": "Awaiting Analysis",
      "weaknesses": "[{\"source\": \"security@huntr.dev\", \"type\": \"Secondary\", \"description\": [{\"lang\": \"en\", \"value\": \"CWE-94\"}]}]"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2024-5826\",\"sourceIdentifier\":\"security@huntr.dev\",\"published\":\"2024-06-27T19:15:17.350\",\"lastModified\":\"2024-11-21T09:48:24.490\",\"vulnStatus\":\"Awaiting Analysis\",\"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.\"}],\"metrics\":{\"cvssMetricV30\":[{\"source\":\"security@huntr.dev\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.0\",\"vectorString\":\"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\",\"baseScore\":9.8,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":5.9}]},\"weaknesses\":[{\"source\":\"security@huntr.dev\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-94\"}]}],\"references\":[{\"url\":\"https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369\",\"source\":\"security@huntr.dev\"},{\"url\":\"https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369\",\"source\":\"af854a3a-2127-422b-91ae-364da2661108\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CVE Program Container\", \"references\": [{\"url\": \"https://huntr.com/bounties/90620087-44ac-4e43-b659-3c5d30889369\", \"tags\": [\"x_transferred\"]}], \"providerMetadata\": {\"orgId\": \"af854a3a-2127-422b-91ae-364da2661108\", \"shortName\": \"CVE\", \"dateUpdated\": \"2024-08-01T21:25:02.677Z\"}}, {\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2024-5826\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2024-06-28T15:19:12.368194Z\"}}}], \"affected\": [{\"cpes\": [\"cpe:2.3:a:vanna-ai:vanna:-:*:*:*:*:*:*:*\"], \"vendor\": \"vanna-ai\", \"product\": \"vanna\", \"versions\": [{\"status\": \"affected\", \"version\": \"0\"}], \"defaultStatus\": \"unknown\"}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2024-06-28T15:26:22.230Z\"}}], \"cna\": {\"title\": \"Remote Code Execution via Prompt Injection in vanna-ai/vanna\", \"source\": {\"advisory\": \"90620087-44ac-4e43-b659-3c5d30889369\", \"discovery\": \"EXTERNAL\"}, \"metrics\": [{\"cvssV3_0\": {\"scope\": \"UNCHANGED\", \"version\": \"3.0\", \"baseScore\": 9.8, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"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/90620087-44ac-4e43-b659-3c5d30889369\"}], \"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.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-94\", \"description\": \"CWE-94 Improper Control of Generation of Code\"}]}], \"providerMetadata\": {\"orgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"shortName\": \"@huntr_ai\", \"dateUpdated\": \"2024-06-27T18:40:37.441Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2024-5826\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2024-08-01T21:25:02.677Z\", \"dateReserved\": \"2024-06-10T22:43:12.603Z\", \"assignerOrgId\": \"c09c270a-b464-47c1-9133-acb35b22c19a\", \"datePublished\": \"2024-06-27T18:40:37.441Z\", \"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.