CVE-2026-61539: Xinference Remote Code Execution Vulnerability

{
  "schema_version" : "1.4.0",
  "id" : "GHSA-x2rj-828p-hx9m",
  "modified" : "2026-08-21T20:56:37Z",
  "published" : "2026-08-21T20:56:37Z",
  "aliases" : [ "CVE-2026-61539" ],
  "summary" : "Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing",
  "details" : "### Summary\n\nXinference 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.\n\n### Details\n\nUsers 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.\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) -> 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__('os').system('touch /tmp/hacked')\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)",
  "severity" : [ {
    "type" : "CVSS_V3",
    "score" : "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "PyPI",
      "name" : "xinference"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "fixed" : "2.7.0"
      } ]
    } ],
    "database_specific" : {
      "last_known_affected_version_range" : "<= 2.5.0"
    }
  } ],
  "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"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-95" ],
    "severity" : "CRITICAL",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-08-21T20:56:37Z",
    "nvd_published_at" : null
  }
}