CVE-2026-61539

CRITICAL
Published Aug 21, 2026 Modified Aug 24, 2026 CWE-95

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.

Is your site exposed to CVE-2026-61539?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

10.0
CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H

EPSS — Exploit Prediction

0.0066
Probability of exploitation
0.50%
Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-95 CWE-95

References

Frequently Asked Questions

What is 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. It has a CVSS v3.1 base score of 10.0 (CRITICAL).
How severe is CVE-2026-61539? +
CVE-2026-61539 has a CVSS v3.1 score of 10.0 out of 10, rated CRITICAL. This is a critical vulnerability that should be patched immediately. The EPSS score is 0.0066, placing it in the 0th percentile for exploitation probability.
How do I check if I'm vulnerable to CVE-2026-61539? +
You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2011-10033

The WordPress plugin is-human <= v1.4.2 contains an eval injection vulnerability in /is-human/engine.php that can be triggered via the 'type' …
CVE-2026-65643

Eval injection in cPanel 11.138.0.0 and earlier allows remote authenticated users to execute arbitrary code as root.
CVE-2026-53875

picklescan before 1.0.3 contains a scanning bypass vulnerability in the scan_pytorch function that allows attackers to embed malicious magic numbers …
CVE-2026-75062

Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection') in the default lf.query Python protocol in Google langfun versions …
CVE-2025-12140

The application contains an insecure 'redirectToUrl' mechanism that incorrectly processes the value of the 'redirectUrlParameter' parameter. The application interprets the …
CVE-2025-4318

The AWS Amplify Studio UI component property expressions in the aws-amplify/amplify-codegen-ui package lack input validation. This could potentially allow an …

Don't wait for an exploit

Scan your website for vulnerabilities like CVE-2026-61539 — free, no signup required.