CVE-2026-61539: Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing

Should you act?

Critical and remotely reachable

No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.

• No confirmed exploitation. It is not in CISA’s KEV catalog and CISA’s SSVC assessment records no known exploitation. That can change quickly after a public write-up; re-check if you are affected.
• EPSS 1.2%, percentile 69: FIRST’s model estimates a 1.2% chance of exploitation activity in the next 30 days, higher than 69% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
• Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
• Only applies if your dependency tree includes xinference (PyPI) <= 2.5.0, fixed in 2.7.0. Check your lockfile, including transitive dependencies.

What it is

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/toolparsers/llama3toolparser.py and xinference/model/llm/utils.py. Requests to /v1/chat/completions with a tools field flow through xinference/api/restfulapi.py, xinference/model/llm/transformers/core.py, handlechatresultnonstreaming(), and postprocesscompletion() before extracttoolcalls() or evalllama3chatarguments() 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.

From the GitHub advisory

Summary

Xinference 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.

Details

Users can interact with deployed models through Xinference's OpenAI-compatible /v1/chat/completions API. The request entry point is implemented in xinference/api/restfulapi.py; non-streaming requests call the model instance's chat() method and return the inference result.

When 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 handlechatresultnonstreaming(). If the request contains a tools field, Xinference calls postprocesscompletion() to parse tool-call output from the model response.

Weakness type: CWE-95.

Product: xinference (PyPI) · Assigned by: GitHub_M · Published: 2026-08-21

Affected and fixed versions

Severity scores

• Attack vector: network (remotely reachable)
• Attack complexity: low
• Privileges required: none (no login)
• User interaction: none
• Scope: changed (can affect other components)

CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.

Exploitation and urgency

• CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
• CISA SSVC assessment: exploitation none, automatable yes, technical impact total.
• FIRST EPSS (model of 2026-10-21): 1.23% probability of exploitation activity in the next 30 days; percentile 69.

Timeline

• 2026-08-21 — CVE record published by GitHub_M
• 2026-08-21 — GitHub-reviewed advisory GHSA-x2rj-828p-hx9m published (critical)
• 2026-08-24 — CVE record last updated

Sources and references

Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.

Vulnerability records

1. GitHub Advisory GHSA-x2rj-828p-hx9m github.com
2. CVE.org record CVE-2026-61539 cve.org
3. NVD entry CVE-2026-61539 nvd.nist.gov

Other references from the CVE record and advisory

1. github.com github.com
2. github.com github.com
3. github.com github.com
4. github.com github.com

Critical PyPI advisories · Today’s Security Digest