CVE-2026-44284 (GCVE-0-2026-44284)

Vulnerability from cvelistv5 – Published: 2026-05-08 22:12 – Updated: 2026-05-11 15:57
VLAI?
Title
FastGPT: Stored MCP tool URL SSRF in FastGPT workflow execution
Summary
FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.
Severity ?
6.3 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
CWE
  • CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
Impacted products
Vendor Product Version
labring FastGPT Affected: < 4.14.17
Create a notification for this product.
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-44284",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-05-11T15:57:46.900457Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-05-11T15:57:51.029Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/labring/FastGPT/pull/6826"
          },
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "FastGPT",
          "vendor": "labring",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 4.14.17"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "LOW",
            "baseScore": 6.3,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "LOW",
            "integrityImpact": "LOW",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-918",
              "description": "CWE-918: Server-Side Request Forgery (SSRF)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-05-08T22:12:39.854Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq"
        },
        {
          "name": "https://github.com/labring/FastGPT/pull/6826",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/labring/FastGPT/pull/6826"
        },
        {
          "name": "https://github.com/labring/FastGPT/commit/c1c6b9520d976d25ed945b5bc4e0768149e6db69",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/labring/FastGPT/commit/c1c6b9520d976d25ed945b5bc4e0768149e6db69"
        },
        {
          "name": "https://github.com/labring/FastGPT/releases/tag/v4.14.17",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/labring/FastGPT/releases/tag/v4.14.17"
        }
      ],
      "source": {
        "advisory": "GHSA-cxxj-99f7-f5wq",
        "discovery": "UNKNOWN"
      },
      "title": "FastGPT: Stored MCP tool URL SSRF in FastGPT workflow execution"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-44284",
    "datePublished": "2026-05-08T22:12:39.854Z",
    "dateReserved": "2026-05-05T17:39:31.112Z",
    "dateUpdated": "2026-05-11T15:57:51.029Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-44284",
      "date": "2026-05-21",
      "epss": "0.00055",
      "percentile": "0.17107"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-44284\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-05-08T23:16:39.507\",\"lastModified\":\"2026-05-12T16:40:21.437\",\"vulnStatus\":\"Deferred\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L\",\"baseScore\":6.3,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"LOW\",\"integrityImpact\":\"LOW\",\"availabilityImpact\":\"LOW\"},\"exploitabilityScore\":2.8,\"impactScore\":3.4}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-918\"}]}],\"references\":[{\"url\":\"https://github.com/labring/FastGPT/commit/c1c6b9520d976d25ed945b5bc4e0768149e6db69\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/labring/FastGPT/pull/6826\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/labring/FastGPT/releases/tag/v4.14.17\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/labring/FastGPT/pull/6826\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"},{\"url\":\"https://github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"cna\": {\"title\": \"FastGPT: Stored MCP tool URL SSRF in FastGPT workflow execution\", \"problemTypes\": [{\"descriptions\": [{\"cweId\": \"CWE-918\", \"lang\": \"en\", \"description\": \"CWE-918: Server-Side Request Forgery (SSRF)\", \"type\": \"CWE\"}]}], \"metrics\": [{\"cvssV3_1\": {\"attackComplexity\": \"LOW\", \"attackVector\": \"NETWORK\", \"availabilityImpact\": \"LOW\", \"baseScore\": 6.3, \"baseSeverity\": \"MEDIUM\", \"confidentialityImpact\": \"LOW\", \"integrityImpact\": \"LOW\", \"privilegesRequired\": \"LOW\", \"scope\": \"UNCHANGED\", \"userInteraction\": \"NONE\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L\", \"version\": \"3.1\"}}], \"references\": [{\"name\": \"https://github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq\", \"tags\": [\"x_refsource_CONFIRM\"], \"url\": \"https://github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq\"}, {\"name\": \"https://github.com/labring/FastGPT/pull/6826\", \"tags\": [\"x_refsource_MISC\"], \"url\": \"https://github.com/labring/FastGPT/pull/6826\"}, {\"name\": \"https://github.com/labring/FastGPT/commit/c1c6b9520d976d25ed945b5bc4e0768149e6db69\", \"tags\": [\"x_refsource_MISC\"], \"url\": \"https://github.com/labring/FastGPT/commit/c1c6b9520d976d25ed945b5bc4e0768149e6db69\"}, {\"name\": \"https://github.com/labring/FastGPT/releases/tag/v4.14.17\", \"tags\": [\"x_refsource_MISC\"], \"url\": \"https://github.com/labring/FastGPT/releases/tag/v4.14.17\"}], \"affected\": [{\"vendor\": \"labring\", \"product\": \"FastGPT\", \"versions\": [{\"version\": \"\u003c 4.14.17\", \"status\": \"affected\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-05-08T22:12:39.854Z\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"FastGPT is an AI Agent building platform. Prior to version 4.14.17, FastGPT had an inconsistent SSRF protection gap in MCP tool URL handling. The direct MCP preview/run endpoints already rejected internal/private network URLs, but the MCP tool create/update endpoints could still save an internal MCP server URL. That stored URL could later be used by workflow execution without revalidating the destination. An authenticated user with permission to create or manage MCP toolsets could store an internal endpoint such as http://localhost:3000/mcp and later cause the FastGPT backend workflow runner to connect to that internal destination. This issue has been patched in version 4.14.17.\"}], \"source\": {\"advisory\": \"GHSA-cxxj-99f7-f5wq\", \"discovery\": \"UNKNOWN\"}}, \"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-44284\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-05-11T15:57:46.900457Z\"}}}], \"references\": [{\"url\": \"https://github.com/labring/FastGPT/pull/6826\", \"tags\": [\"exploit\"]}, {\"url\": \"https://github.com/labring/FastGPT/security/advisories/GHSA-cxxj-99f7-f5wq\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-05-11T15:57:41.569Z\"}}]}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-44284\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"state\": \"PUBLISHED\", \"assignerShortName\": \"GitHub_M\", \"dateReserved\": \"2026-05-05T17:39:31.112Z\", \"datePublished\": \"2026-05-08T22:12:39.854Z\", \"dateUpdated\": \"2026-05-11T15:57:51.029Z\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

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.



Detection rules are retrieved from Rulezet.