{"id":"CVE-2026-61539","state":"PUBLISHED","title":"Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing","description":"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.","publishedAt":"2026-08-21T20:37:02.633Z","updatedAt":"2026-08-24T19:45:13.875Z","severity":{"score":10,"label":"Critical","version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H","source":"GitHub_M"},"assigner":"GitHub_M","products":["xorbitsai inference"],"affected":[{"vendor":"xorbitsai","product":"inference","versions":[{"version":"< 2.7.0","status":"affected"}]}],"references":["https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m","https://github.com/xorbitsai/inference/pull/4786","https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42","https://github.com/xorbitsai/inference/releases/tag/v2.7.0"],"weaknesses":["CWE-95"],"ingestedAt":"2026-10-29T20:12:32.778Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/61xxx/CVE-2026-61539.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-61539","state":"PUBLISHED","datePublished":"2026-08-21T20:37:02.633Z","dateUpdated":"2026-08-24T19:45:13.875Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-07-10T16:27:03.093Z"},"containers":{"cna":{"title":"Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing","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."}],"affected":[{"vendor":"xorbitsai","product":"inference","versions":[{"version":"< 2.7.0","status":"affected"}]}],"references":[{"url":"https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m","name":"https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m","tags":["x_refsource_CONFIRM"]},{"url":"https://github.com/xorbitsai/inference/pull/4786","name":"https://github.com/xorbitsai/inference/pull/4786","tags":["x_refsource_MISC"]},{"url":"https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42","name":"https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42","tags":["x_refsource_MISC"]},{"url":"https://github.com/xorbitsai/inference/releases/tag/v2.7.0","name":"https://github.com/xorbitsai/inference/releases/tag/v2.7.0","tags":["x_refsource_MISC"]}],"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","lang":"en","description":"CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')","type":"CWE"}]}],"providerMetadata":{"shortName":"GitHub_M","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateUpdated":"2026-08-21T20:37:02.633Z"},"source":{"advisory":"GHSA-x2rj-828p-hx9m","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-08-24T19:45:03.839039Z","id":"CVE-2026-61539","options":[{"Exploitation":"none"},{"Automatable":"yes"},{"Technical Impact":"total"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-08-24T19:45:13.875Z"}}]}}}