CVE-2026-61539

CRITICALPre-NVD 10.010.0—
EchelonGraph scoreMEDIUM confidence

This critical-severity CVE scores 10.0 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.7%, top 51% of all CVEs by exploit prediction. GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).

Triggered by: NVD CVSS baseline
Sources: epss, secondary
Trending — 3 sources updated this week
10.0EG
EchelonGraph verdictPlan a fixSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 1%CVSS: 10.0Exploit: None knownExposed: 0

No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.

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.

CVSS v3
10.0
EG Score
10.0(medium)
EG Risk
60(Track)
EG Risk 60/100SSVC: Track

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed
Severity100% × 45%
Exploitation1% × 40%
Automatability100% × 15%
Action: Routine — remediate on your standard cadence.
EPSS PROB
1%
EPSS %ILE
49%
KEV
Not listed

Published

August 21, 2026

Last Modified

August 24, 2026

Advisory Details (4)

Auto-updated Aug 24, 2026
Patch available. Sources: github_commit, github_pr, github_release, github.
github Patch Available

Remote code execution via unsafe `eval()` in Llama3 tool-call parsing · Advisory · xorbitsai/inference · GitHub

https://github.com/xorbitsai/inference/security/advisories/GHSA-x2rj-828p-hx9m
github_release Patch Available

v2.7.0

Patch available: xorbitsai/inference v2.7.0

https://github.com/xorbitsai/inference/releases/tag/v2.7.0
github_pr Patch Available

fix: replace eval() with safe alternatives to prevent RCE in tool parsers

Patch available: xorbitsai/inference v2.7.0 (PR #4786 merged 2026-04-14)

https://github.com/xorbitsai/inference/pull/4786
github_commit Patch Available

commit 1b3d220f342c (xorbitsai/inference)

Patch available: xorbitsai/inference v2.7.0 (contains commit 1b3d220f342c)

https://github.com/xorbitsai/inference/commit/1b3d220f342ce68d34cec4586d9409d457dadc42

Vendor Advisories for CVE-2026-61539(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFixed inDependents
xinference0.0.0 ... 2.5.0 (138 versions)2.7.0—

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 11× in last 7d / 11× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-08-25 15:32 UTCEG score recompute
  2. 2026-08-25 13:49 UTCEPSS rescore
  3. 2026-08-24 20:28 UTCEG score recompute
  4. 2026-08-24 19:51 UTCEG score recompute
  5. 2026-08-24 18:03 UTCEG score recompute
  6. 2026-08-24 10:25 UTCEG score recompute
  7. 2026-08-23 03:54 UTCEG score recompute
  8. 2026-08-23 00:19 UTCEPSS rescore
  9. 2026-08-21 21:24 UTCEG score recompute
  10. 2026-08-21 20:44 UTCEG score recompute
  11. 2026-08-21 20:44 UTCMITRE cvelistV5first tracked

Frequently asked(5)

What is CVE-2026-61539?
CVE-2026-61539 is a critical vulnerability published on August 21, 2026. 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…
When was CVE-2026-61539 disclosed?
CVE-2026-61539 was first published in the National Vulnerability Database on August 21, 2026, with the most recent update on August 24, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-61539 actively exploited?
CVE-2026-61539 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 1% probability of exploitation in the next 30 days, which ranks it in the top 51.3% of all scored CVEs.
What is the CVSS score of CVE-2026-61539?
CVE-2026-61539 has a CVSS v3 base score of 10.0 (NVD).
How do I remediate CVE-2026-61539?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-61539, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-61539

Explore →

Is Your Infrastructure Affected by CVE-2026-61539?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Start Free Scan →Browse All CVEs