CVE-2026-61539

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.

CVSS v3 10.0 CRITICAL

10.0^/10

CVSS v3 : CRITICAL

Vector :

Exploitability : 3.9 / Impact : 6.0

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope CHANGED

References

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

Configurations

No configuration.

History

No history.

Information

Published : 2026-08-21 21:17

Updated : 2026-08-24 20:16

NVD link : CVE-2026-61539

Mitre link : CVE-2026-61539

CVE.ORG link : CVE-2026-61539

JSON object : View

Products Affected

No product.

CWE

CWE-95

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

{"id": "CVE-2026-61539", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-61539", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "yes"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-08-24T19:45:03.839039Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 10.0, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 6.0, "exploitabilityScore": 3.9}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "xorbitsai", "product": "inference", "versions": [{"status": "affected", "version": "< 2.7.0"}]}]}], "published": "2026-08-21T21:17:00.867", "references": [{"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", "source": "security-advisories@github.com"}], "vulnStatus": "Received", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-95"}]}], "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."}], "lastModified": "2026-08-24T20:16:52.137", "sourceIdentifier": "security-advisories@github.com"}