GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration

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

Vulnerability from cvelistv5 – Published: 2026-08-21 20:37 – Updated: 2026-08-24 19:45
VLAI
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
References
Impacted products
Vendor Product Version CPE status
xorbitsai inference Affected: < 2.7.0
guessed Create a notification for this product.
Show details on NVD website
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": "2026-09-15",
      "epss": "0.00657",
      "percentile": "0.49589"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-61539\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-08-21T21:17:00.867\",\"lastModified\":\"2026-08-24T20:16:52.137\",\"vulnStatus\":\"Received\",\"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.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"xorbitsai\",\"product\":\"inference\",\"versions\":[{\"version\":\"\u003c 2.7.0\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H\",\"baseScore\":10.0,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":6.0}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-08-24T19:45:03.839039Z\",\"id\":\"CVE-2026-61539\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"yes\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-95\"}]}],\"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\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-61539\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-08-24T19:45:03.839039Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-08-24T19:45:10.179Z\"}}], \"cna\": {\"title\": \"Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing\", \"source\": {\"advisory\": \"GHSA-x2rj-828p-hx9m\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 10, \"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\"}}], \"affected\": [{\"vendor\": \"xorbitsai\", \"product\": \"inference\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 2.7.0\"}]}], \"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\"]}], \"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.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-95\", \"description\": \"CWE-95: Improper Neutralization of Directives in Dynamically Evaluated Code (\u0027Eval Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-08-21T20:37:02.633Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-61539\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-08-24T19:45:13.875Z\", \"dateReserved\": \"2026-07-10T16:27:03.093Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-08-21T20:37:02.633Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

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.


Detection rules are retrieved from Rulezet.


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.