Vulnerability-Lookup

CVE-2026-61539 (GCVE-0-2026-61539)

Vulnerability from cvelistv5 – Published: 2026-08-21 20:37 – Updated: 2026-08-24 19:45

Title

Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing

Summary

Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval() in xinference/model/llm/tool_parsers/llama3_tool_parser.py and xinference/model/llm/utils.py. Requests to /v1/chat/completions with a tools field flow through xinference/api/restful_api.py, xinference/model/llm/transformers/core.py, handle_chat_result_non_streaming(), and _post_process_completion() before extract_tool_calls() or _eval_llama3_chat_arguments() evaluates the model-generated Python expression. An unauthenticated remote attacker can influence that output through a crafted prompt and execute commands in the Xinference server process context. This issue is fixed in version 2.7.0.

Severity

10 (Critical)


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

SSVC

Exploitation: none Automatable: yes Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-08-24 19:45 UTC

CWE

CWE-95 - Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7637 records in the last 180 days details

References

4 references

URL	Tags
https://github.com/xorbitsai/inference/security/a…	x_refsource_CONFIRM
https://github.com/xorbitsai/inference/pull/4786	x_refsource_MISC
https://github.com/xorbitsai/inference/commit/1b3…	x_refsource_MISC
https://github.com/xorbitsai/inference/releases/t…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version	CPE status
xorbitsai	inference	Affected: < 2.7.0	guessed

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-61539",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-24T19:45:03.839039Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-24T19:45:13.875Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "inference",
          "vendor": "xorbitsai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 2.7.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval() in xinference/model/llm/tool_parsers/llama3_tool_parser.py and xinference/model/llm/utils.py. Requests to /v1/chat/completions with a tools field flow through xinference/api/restful_api.py, xinference/model/llm/transformers/core.py, handle_chat_result_non_streaming(), and _post_process_completion() before extract_tool_calls() or _eval_llama3_chat_arguments() evaluates the model-generated Python expression. An unauthenticated remote attacker can influence that output through a crafted prompt and execute commands in the Xinference server process context. This issue is fixed in version 2.7.0."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 10,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-95",
              "description": "CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-21T20:37:02.633Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m"
        },
        {
          "name": "https://github.com/xorbitsai/inference/pull/4786",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/xorbitsai/inference/pull/4786"
        },
        {
          "name": "https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42"
        },
        {
          "name": "https://github.com/xorbitsai/inference/releases/tag/v2.7.0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/xorbitsai/inference/releases/tag/v2.7.0"
        }
      ],
      "source": {
        "advisory": "GHSA-x2rj-828p-hx9m",
        "discovery": "UNKNOWN"
      },
      "title": "Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-61539",
    "datePublished": "2026-08-21T20:37:02.633Z",
    "dateReserved": "2026-07-10T16:27:03.093Z",
    "dateUpdated": "2026-08-24T19:45:13.875Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-61539",
      "date": "2026-10-15",
      "epss": "0.01226",
      "percentile": "0.68294"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "inference",
                "vendor": "xorbitsai",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 2.7.0"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval() in xinference/model/llm/tool_parsers/llama3_tool_parser.py and xinference/model/llm/utils.py. Requests to /v1/chat/completions with a tools field flow through xinference/api/restful_api.py, xinference/model/llm/transformers/core.py, handle_chat_result_non_streaming(), and _post_process_completion() before extract_tool_calls() or _eval_llama3_chat_arguments() evaluates the model-generated Python expression. An unauthenticated remote attacker can influence that output through a crafted prompt and execute commands in the Xinference server process context. This issue is fixed in version 2.7.0."
          },
          {
            "lang": "es",
            "value": "Xinference es una API de inferencia para ejecutar modelos de c\u00f3digo abierto, de voz y multimodales. En las versiones 2.5.0 y anteriores, Xinference pasa la salida de llamadas a herramientas de Llama3 influenciada por el atacante a eval() en xinference/model/llm/tool_parsers/llama3_tool_parser.py y xinference/model/llm/utils.py. Las solicitudes a /v1/chat/completions con un campo \u0027tools\u0027 fluyen a trav\u00e9s de xinference/api/restful_api.py, xinference/model/llm/transformers/core.py, handle_chat_result_non_streaming() y _post_process_completion() antes de que extract_tool_calls() o _eval_llama3_chat_arguments() eval\u00faen la expresi\u00f3n Python generada por el modelo. Un atacante remoto no autenticado puede influenciar esa salida a trav\u00e9s de un prompt manipulado y ejecutar comandos en el contexto del proceso del servidor de Xinference. Este problema se ha solucionado en la versi\u00f3n 2.7.0."
          }
        ],
        "id": "CVE-2026-61539",
        "lastModified": "2026-10-12T16:10:00.220",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 10.0,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
                "version": "3.1"
              },
              "exploitabilityScore": 3.9,
              "impactScore": 6.0,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-61539",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "yes"
                  },
                  {
                    "technicalImpact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-24T19:45:03.839039Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-08-21T21:17:00.867",
        "references": [
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/xorbitsai/inference/pull/4786"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/xorbitsai/inference/releases/tag/v2.7.0"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Deferred",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-95"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-61539",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-08-24T19:45:03.839039Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-08-24T19:45:10.179Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "inference",
              "vendor": "xorbitsai",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 2.7.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval() in xinference/model/llm/tool_parsers/llama3_tool_parser.py and xinference/model/llm/utils.py. Requests to /v1/chat/completions with a tools field flow through xinference/api/restful_api.py, xinference/model/llm/transformers/core.py, handle_chat_result_non_streaming(), and _post_process_completion() before extract_tool_calls() or _eval_llama3_chat_arguments() evaluates the model-generated Python expression. An unauthenticated remote attacker can influence that output through a crafted prompt and execute commands in the Xinference server process context. This issue is fixed in version 2.7.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 10,
                "baseSeverity": "CRITICAL",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "CHANGED",
                "userInteraction": "NONE",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-95",
                  "description": "CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-08-21T20:37:02.633Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m"
            },
            {
              "name": "https://github.com/xorbitsai/inference/pull/4786",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/xorbitsai/inference/pull/4786"
            },
            {
              "name": "https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42"
            },
            {
              "name": "https://github.com/xorbitsai/inference/releases/tag/v2.7.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/xorbitsai/inference/releases/tag/v2.7.0"
            }
          ],
          "source": {
            "advisory": "GHSA-x2rj-828p-hx9m",
            "discovery": "UNKNOWN"
          },
          "title": "Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-61539",
        "datePublished": "2026-08-21T20:37:02.633Z",
        "dateReserved": "2026-07-10T16:27:03.093Z",
        "dateUpdated": "2026-08-24T19:45:13.875Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-61539

Vulnerability from fkie_nvd - Published: 2026-08-21 21:17 - Updated: 2026-10-12 16:10

Severity

10.0 (Critical) - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

Summary

References

	URL	Tags
	security-advisories@github.com	https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42
	security-advisories@github.com	https://github.com/xorbitsai/inference/pull/4786
	security-advisories@github.com	https://github.com/xorbitsai/inference/releases/tag/v2.7.0
	security-advisories@github.com	https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m

Impacted products

	Vendor	Product	Version

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "inference",
          "vendor": "xorbitsai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 2.7.0"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval() in xinference/model/llm/tool_parsers/llama3_tool_parser.py and xinference/model/llm/utils.py. Requests to /v1/chat/completions with a tools field flow through xinference/api/restful_api.py, xinference/model/llm/transformers/core.py, handle_chat_result_non_streaming(), and _post_process_completion() before extract_tool_calls() or _eval_llama3_chat_arguments() evaluates the model-generated Python expression. An unauthenticated remote attacker can influence that output through a crafted prompt and execute commands in the Xinference server process context. This issue is fixed in version 2.7.0."
    },
    {
      "lang": "es",
      "value": "Xinference es una API de inferencia para ejecutar modelos de c\u00f3digo abierto, de voz y multimodales. En las versiones 2.5.0 y anteriores, Xinference pasa la salida de llamadas a herramientas de Llama3 influenciada por el atacante a eval() en xinference/model/llm/tool_parsers/llama3_tool_parser.py y xinference/model/llm/utils.py. Las solicitudes a /v1/chat/completions con un campo \u0027tools\u0027 fluyen a trav\u00e9s de xinference/api/restful_api.py, xinference/model/llm/transformers/core.py, handle_chat_result_non_streaming() y _post_process_completion() antes de que extract_tool_calls() o _eval_llama3_chat_arguments() eval\u00faen la expresi\u00f3n Python generada por el modelo. Un atacante remoto no autenticado puede influenciar esa salida a trav\u00e9s de un prompt manipulado y ejecutar comandos en el contexto del proceso del servidor de Xinference. Este problema se ha solucionado en la versi\u00f3n 2.7.0."
    }
  ],
  "id": "CVE-2026-61539",
  "lastModified": "2026-10-12T16:10:00.220",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 10.0,
          "baseSeverity": "CRITICAL",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "scope": "CHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 6.0,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-61539",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-08-24T19:45:03.839039Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-08-21T21:17:00.867",
  "references": [
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/xorbitsai/inference/pull/4786"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/xorbitsai/inference/releases/tag/v2.7.0"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-95"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-X2RJ-828P-HX9M

Vulnerability from github – Published: 2026-08-21 20:56 – Updated: 2026-08-21 20:56

Summary

Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing

Details

Summary

Xinference used Python's unsafe eval() function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to return a Python expression. Xinference then evaluates that expression on the server while post-processing the tool-call result. In the tested default deployment, authentication was not enabled, so the vulnerability was exploitable by an unauthenticated remote attacker through the /v1/chat/completions endpoint.

Details

Users can interact with deployed models through Xinference's OpenAI-compatible /v1/chat/completions API. The request entry point is implemented in xinference/api/restful_api.py; non-streaming requests call the model instance's chat() method and return the inference result.

When the Transformers backend is used, inference results flow through the batching logic in xinference/model/llm/transformers/core.py. Non-streaming chat results are handled by handle_chat_result_non_streaming(). If the request contains a tools field, Xinference calls _post_process_completion() to parse tool-call output from the model response.

The Llama3 tool-call parser is implemented in xinference/model/llm/tool_parsers/llama3_tool_parser.py. In affected versions, extract_tool_calls() parsed model output with eval():

def extract_tool_calls(
    self, model_output: str
) -> List[Tuple[Optional[str], Optional[str], Optional[Dict[str, Any]]]]:
    try:
        data = eval(model_output, {}, {})
        return [(None, data["name"], data["parameters"])]
    except Exception:
        return [(model_output, None, None)]

The intended behavior was to convert a Python dictionary-like string generated by the model into a dictionary object. However, eval() executes the input as a Python expression, and eval(model_output, {}, {}) is not a security sandbox. If an attacker can influence the model output through prompt injection or direct chat input, the attacker can cause the model to return an expression such as:

__import__('os').system('touch /tmp/hacked')

When the expression reaches eval(), it is executed in the Xinference server process context. The harmless touch /tmp/hacked command can be replaced with other payloads, such as a reverse shell, malware download, sensitive file read, or lateral-movement payload.

Score

Severity: Critical

CVSS v3.1: 10.0

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

Rationale:

AV:N: the vulnerable API is remotely reachable over the network;
AC:L: exploitation only requires a crafted chat-completion request and tool-call parameter;
PR:N: the tested default configuration did not require authentication;
UI:N: no user interaction is required;
S:C: command execution can affect resources beyond the Xinference application boundary;
C:H/I:H/A:H: remote code execution can fully compromise confidentiality, integrity, and availability.

Credit

This vulnerability was discovered by:

XlabAI Team of Tencent Xuanwu Lab (xlabai@tencent.com)
Atuin Automated Vulnerability Discovery Engine
Guannan Wang (wgnbuaa@gmail.com), Zhanpeng Liu (pkugenuine@gmail.com), Guancheng Li (lgcpku@gmail.com)

Severity

10.0 (Critical)


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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 2.5.0"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "xinference"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "2.7.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-61539"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-95"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-08-21T20:56:37Z",
    "nvd_published_at": null,
    "severity": "CRITICAL"
  },
  "details": "### Summary\n\nXinference used Python\u0027s unsafe `eval()` function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to return a Python expression. Xinference then evaluates that expression on the server while post-processing the tool-call result. In the tested default deployment, authentication was not enabled, so the vulnerability was exploitable by an unauthenticated remote attacker through the `/v1/chat/completions` endpoint.\n\n### Details\n\nUsers can interact with deployed models through Xinference\u0027s OpenAI-compatible `/v1/chat/completions` API. The request entry point is implemented in `xinference/api/restful_api.py`; non-streaming requests call the model instance\u0027s `chat()` method and return the inference result.\n\nWhen the Transformers backend is used, inference results flow through the batching logic in `xinference/model/llm/transformers/core.py`. Non-streaming chat results are handled by `handle_chat_result_non_streaming()`. If the request contains a `tools` field, Xinference calls `_post_process_completion()` to parse tool-call output from the model response.\n\nThe Llama3 tool-call parser is implemented in `xinference/model/llm/tool_parsers/llama3_tool_parser.py`. In affected versions, `extract_tool_calls()` parsed model output with `eval()`:\n\n```python\ndef extract_tool_calls(\n    self, model_output: str\n) -\u003e List[Tuple[Optional[str], Optional[str], Optional[Dict[str, Any]]]]:\n    try:\n        data = eval(model_output, {}, {})\n        return [(None, data[\"name\"], data[\"parameters\"])]\n    except Exception:\n        return [(model_output, None, None)]\n```\n\nThe intended behavior was to convert a Python dictionary-like string generated by the model into a dictionary object. However, `eval()` executes the input as a Python expression, and `eval(model_output, {}, {})` is not a security sandbox. If an attacker can influence the model output through prompt injection or direct chat input, the attacker can cause the model to return an expression such as:\n\n```python\n__import__(\u0027os\u0027).system(\u0027touch /tmp/hacked\u0027)\n```\n\nWhen the expression reaches `eval()`, it is executed in the Xinference server process context. The harmless `touch /tmp/hacked` command can be replaced with other payloads, such as a reverse shell, malware download, sensitive file read, or lateral-movement payload.\n\n### Score\n\nSeverity: Critical\n\nCVSS v3.1: 10.0\n\nVector: `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`\n\nRationale:\n\n- AV:N: the vulnerable API is remotely reachable over the network;\n- AC:L: exploitation only requires a crafted chat-completion request and tool-call parameter;\n- PR:N: the tested default configuration did not require authentication;\n- UI:N: no user interaction is required;\n- S:C: command execution can affect resources beyond the Xinference application boundary;\n- C:H/I:H/A:H: remote code execution can fully compromise confidentiality, integrity, and availability.\n\n### Credit\n\nThis vulnerability was discovered by:\n\n- XlabAI Team of Tencent Xuanwu Lab (xlabai@tencent.com)\n- Atuin Automated Vulnerability Discovery Engine\n- Guannan Wang (wgnbuaa@gmail.com), Zhanpeng Liu (pkugenuine@gmail.com), Guancheng Li (lgcpku@gmail.com)",
  "id": "GHSA-x2rj-828p-hx9m",
  "modified": "2026-08-21T20:56:37Z",
  "published": "2026-08-21T20:56:37Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m"
    },
    {
      "type": "WEB",
      "url": "https://github.com/xorbitsai/inference/pull/4786"
    },
    {
      "type": "WEB",
      "url": "https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/xorbitsai/inference"
    },
    {
      "type": "WEB",
      "url": "https://github.com/xorbitsai/inference/releases/tag/v2.7.0"
    }
  ],
  "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:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing"
}

PYSEC-2026-3946

Vulnerability from pysec - Published: 2026-09-10 09:44 - Updated: 2026-09-10 11:02

Details

Summary

Details

The Llama3 tool-call parser is implemented in xinference/model/llm/tool_parsers/llama3_tool_parser.py. In affected versions, extract_tool_calls() parsed model output with eval():

def extract_tool_calls(
    self, model_output: str
) -> List[Tuple[Optional[str], Optional[str], Optional[Dict[str, Any]]]]:
    try:
        data = eval(model_output, {}, {})
        return [(None, data["name"], data["parameters"])]
    except Exception:
        return [(model_output, None, None)]

__import__('os').system('touch /tmp/hacked')

Score

Severity: Critical

CVSS v3.1: 10.0

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

Rationale:

AV:N: the vulnerable API is remotely reachable over the network;
AC:L: exploitation only requires a crafted chat-completion request and tool-call parameter;
PR:N: the tested default configuration did not require authentication;
UI:N: no user interaction is required;
S:C: command execution can affect resources beyond the Xinference application boundary;
C:H/I:H/A:H: remote code execution can fully compromise confidentiality, integrity, and availability.

Credit

This vulnerability was discovered by:

XlabAI Team of Tencent Xuanwu Lab (xlabai@tencent.com)
Atuin Automated Vulnerability Discovery Engine
Guannan Wang (wgnbuaa@gmail.com), Zhanpeng Liu (pkugenuine@gmail.com), Guancheng Li (lgcpku@gmail.com)

Severity

10.0 (Critical)


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

Impacted products

Name	purl
xinference	pkg:pypi/xinference

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "xinference",
        "purl": "pkg:pypi/xinference"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "2.7.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.0.0",
        "0.0.1",
        "0.0.2",
        "0.0.3",
        "0.0.4",
        "0.0.5",
        "0.0.6",
        "0.1.0",
        "0.1.1",
        "0.1.2",
        "0.1.3",
        "0.10.0",
        "0.10.1",
        "0.10.2",
        "0.10.2.post1",
        "0.10.3",
        "0.11.0",
        "0.11.1",
        "0.11.2",
        "0.11.2.post1",
        "0.11.3",
        "0.12.0",
        "0.12.1",
        "0.12.2",
        "0.12.2.post1",
        "0.12.3",
        "0.13.0",
        "0.13.1",
        "0.13.2",
        "0.13.3",
        "0.13.4",
        "0.14.0",
        "0.14.0.post1",
        "0.14.1",
        "0.14.1.post1",
        "0.14.2",
        "0.14.3",
        "0.14.4",
        "0.14.4.post1",
        "0.15.0",
        "0.15.1",
        "0.15.2",
        "0.15.3",
        "0.15.4",
        "0.16.0",
        "0.16.1",
        "0.16.2",
        "0.16.3",
        "0.2.0",
        "0.2.1",
        "0.2.2",
        "0.2.3",
        "0.3.0",
        "0.4.0",
        "0.4.1",
        "0.4.2",
        "0.4.3",
        "0.4.4",
        "0.5.0",
        "0.5.1",
        "0.5.2",
        "0.5.3",
        "0.5.4",
        "0.5.5",
        "0.5.6",
        "0.6.0",
        "0.6.1",
        "0.6.2",
        "0.6.3",
        "0.6.4",
        "0.6.5",
        "0.7.0",
        "0.7.1",
        "0.7.2",
        "0.7.3",
        "0.7.3.1",
        "0.7.4",
        "0.7.4.1",
        "0.7.5",
        "0.8.0",
        "0.8.1",
        "0.8.2",
        "0.8.3",
        "0.8.3.1",
        "0.8.4",
        "0.8.5",
        "0.9.0",
        "0.9.1",
        "0.9.2",
        "0.9.3",
        "0.9.4",
        "1.0.0",
        "1.0.1",
        "1.1.0",
        "1.1.1",
        "1.10.0",
        "1.10.1",
        "1.11.0",
        "1.11.0.post1",
        "1.12.0",
        "1.13.0",
        "1.14.0",
        "1.15.0",
        "1.16.0",
        "1.17.0",
        "1.17.1",
        "1.2.0",
        "1.2.1",
        "1.2.2",
        "1.3.0",
        "1.3.0.post1",
        "1.3.0.post2",
        "1.3.1",
        "1.3.1.post1",
        "1.4.0",
        "1.4.1",
        "1.5.0",
        "1.5.0.post1",
        "1.5.0.post2",
        "1.5.1",
        "1.6.0",
        "1.6.0.post1",
        "1.6.1",
        "1.7.0",
        "1.7.0.post1",
        "1.7.1",
        "1.7.1.post1",
        "1.8.0",
        "1.8.1",
        "1.8.1rc1",
        "1.9.0",
        "1.9.1",
        "2.0.0",
        "2.1.0",
        "2.2.0",
        "2.3.0",
        "2.4.0",
        "2.5.0"
      ]
    }
  ],
  "aliases": [
    "CVE-2026-61539",
    "GHSA-x2rj-828p-hx9m"
  ],
  "details": "### Summary\n\nXinference used Python\u0027s unsafe `eval()` function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to return a Python expression. Xinference then evaluates that expression on the server while post-processing the tool-call result. In the tested default deployment, authentication was not enabled, so the vulnerability was exploitable by an unauthenticated remote attacker through the `/v1/chat/completions` endpoint.\n\n### Details\n\nUsers can interact with deployed models through Xinference\u0027s OpenAI-compatible `/v1/chat/completions` API. The request entry point is implemented in `xinference/api/restful_api.py`; non-streaming requests call the model instance\u0027s `chat()` method and return the inference result.\n\nWhen the Transformers backend is used, inference results flow through the batching logic in `xinference/model/llm/transformers/core.py`. Non-streaming chat results are handled by `handle_chat_result_non_streaming()`. If the request contains a `tools` field, Xinference calls `_post_process_completion()` to parse tool-call output from the model response.\n\nThe Llama3 tool-call parser is implemented in `xinference/model/llm/tool_parsers/llama3_tool_parser.py`. In affected versions, `extract_tool_calls()` parsed model output with `eval()`:\n\n```python\ndef extract_tool_calls(\n    self, model_output: str\n) -\u003e List[Tuple[Optional[str], Optional[str], Optional[Dict[str, Any]]]]:\n    try:\n        data = eval(model_output, {}, {})\n        return [(None, data[\"name\"], data[\"parameters\"])]\n    except Exception:\n        return [(model_output, None, None)]\n```\n\nThe intended behavior was to convert a Python dictionary-like string generated by the model into a dictionary object. However, `eval()` executes the input as a Python expression, and `eval(model_output, {}, {})` is not a security sandbox. If an attacker can influence the model output through prompt injection or direct chat input, the attacker can cause the model to return an expression such as:\n\n```python\n__import__(\u0027os\u0027).system(\u0027touch /tmp/hacked\u0027)\n```\n\nWhen the expression reaches `eval()`, it is executed in the Xinference server process context. The harmless `touch /tmp/hacked` command can be replaced with other payloads, such as a reverse shell, malware download, sensitive file read, or lateral-movement payload.\n\n### Score\n\nSeverity: Critical\n\nCVSS v3.1: 10.0\n\nVector: `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H`\n\nRationale:\n\n- AV:N: the vulnerable API is remotely reachable over the network;\n- AC:L: exploitation only requires a crafted chat-completion request and tool-call parameter;\n- PR:N: the tested default configuration did not require authentication;\n- UI:N: no user interaction is required;\n- S:C: command execution can affect resources beyond the Xinference application boundary;\n- C:H/I:H/A:H: remote code execution can fully compromise confidentiality, integrity, and availability.\n\n### Credit\n\nThis vulnerability was discovered by:\n\n- XlabAI Team of Tencent Xuanwu Lab (xlabai@tencent.com)\n- Atuin Automated Vulnerability Discovery Engine\n- Guannan Wang (wgnbuaa@gmail.com), Zhanpeng Liu (pkugenuine@gmail.com), Guancheng Li (lgcpku@gmail.com)",
  "id": "PYSEC-2026-3946",
  "modified": "2026-09-10T11:02:37.167860Z",
  "published": "2026-09-10T09:44:52.936049Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m"
    },
    {
      "type": "WEB",
      "url": "https://github.com/xorbitsai/inference/pull/4786"
    },
    {
      "type": "WEB",
      "url": "https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/xorbitsai/inference"
    },
    {
      "type": "WEB",
      "url": "https://github.com/xorbitsai/inference/releases/tag/v2.7.0"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/xinference"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-x2rj-828p-hx9m"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-61539"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing"
}

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

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-2026-61539 (GCVE-0-2026-61539)

FKIE_CVE-2026-61539

GHSA-X2RJ-828P-HX9M

Summary

Details

Score

Credit

PYSEC-2026-3946

Summary

Details

Score

Credit

Tags

Sightings

Nomenclature

Vulnerability timeline

Related by attack behaviour