CVE-2026-61539 json
Xinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsing
published 2mo ago modified 30d ago also EUVD-2026-64146 , GHSA-x2rj-828p-hx9m , PYSEC-2026-3946
- cvss
- 10.0
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 1.2%
- EPSS 1.2% chance of exploitation in 30 days, percentile 69%
- public exploits
- 0
- none known
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.
Patch / fix
- pypi xinference 2.7.0
- xinference xinference 2.7.0
Is CVE-2026-61539 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerCISA SSVC
- Exploitation
- none
- Automatable
- yes
- Technical impact
- total
- Assessed
- 2mo ago
Exploit prediction
1.23% chance of exploitation in the next 30 days, higher than 69% of all scored CVEs (FIRST EPSS, 2026-11-11).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 10.0 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H |
| GitHub | 3.1 | 10.0 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H |
| OSV | 3.1 | 10.0 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | xinference | <2.7.0 |
2.7.0 |
Affected products
- xorbitsai inference
Classification
- Weakness
-
- CWE-95 Improper Neutralization of Directives in Dynamically Evaluated Code
References
-
github.com
/xorbitsai/inference/pull/4786
web
-
github.com
/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42
web
-
github.com
/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m
web
-
github.com
/xorbitsai/inference/releases/tag/v2.7.0
web
-
github.com
/xorbitsai/inference
package
-
pypi.org
/project/xinference
package
-
github.com
/advisories/GHSA-x2rj-828p-hx9m
advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-61539
advisory
Sources
- CVE List CVE-2026-61539
- GitHub Advisory GHSA-x2rj-828p-hx9m
- NVD CVE-2026-61539
- OSV PYSEC-2026-3946
Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.