CVE-2026-92983

HIGHPre-NVD 7.57.5—
EchelonGraph scoreHIGH confidence

Score 7.5 from GitHub Security Advisory (severity: HIGH) published 2026-09-17. a secondary CVSS source baseline 7.5; sources differ by 0.0.

Triggered by: GitHub Security Advisory CVSS
Sources: epss, ghsa, secondary
Trending — 4 sources updated this weekElevated
7.5EG
EchelonGraph verdictPlan a fixSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0%CVSS: 7.5Exploit: Elevated riskExposed: 0

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

InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys. Unauthenticated attackers can send completion requests to the proxy endpoint that accumulate unreleased scheduler metadata and memory until the prefill worker is out-of-memory killed.

CVSS v3
7.5
EG Score
7.5(high)
EG Risk
65(Attend)
EG Risk 65/100SSVC: Attend

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
Severity75% × 45%
Exploitation40% × 40%
Automatability100% × 15%
Action: Remediate soon — notable exploitation risk.
EPSS PROB
0%
EPSS %ILE
30%
KEV
Not listed

Published

September 17, 2026

Last Modified

September 18, 2026

Advisory Details (4)

Auto-updated Sep 17, 2026
No patch confirmed yet.
generic

InternLM LMDeploy through 0.17.0 Memory Exhaustion via Session ID Mismatch | Advisories | VulnCheck

https://www.vulncheck.com/advisories/internlm-lmdeploy-through-0.17.0-memory-exhaustion-via-session-id-mismatch
generic

lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.py at v0.17.0 · InternLM/lmdeploy · GitHub

https://github.com/InternLM/lmdeploy/blob/v0.17.0/lmdeploy/pytorch/disagg/conn/engine_conn.py#L93-L99
generic

GitHub - InternLM/lmdeploy: LMDeploy is a toolkit for compressing, deploying, and serving LLMs. · GitHub

https://github.com/InternLM/lmdeploy
generic

[Bug] DistServe Proxy requests can leak Prefill scheduler metadata and OOM the Prefill engine · Issue #4967 · InternLM/lmdeploy · GitHub

https://github.com/InternLM/lmdeploy/issues/4967

Vendor Advisories for CVE-2026-92983(1)

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

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 14× in last 7d / 14× 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. 2026-09-19 18:50 UTCEG score recompute
  2. 2026-09-19 18:49 UTCGHSA enrichment
  3. 2026-09-19 07:42 UTCGHSA enrichment
  4. 2026-09-18 20:35 UTCEG score recompute
  5. 2026-09-18 20:35 UTCGHSA enrichment
  6. 2026-09-18 19:29 UTCEG score recompute
  7. 2026-09-18 19:29 UTCGHSA enrichment
  8. 2026-09-18 19:28 UTCEPSS rescore
  9. 2026-09-18 13:36 UTCGHSA enrichment
  10. 2026-09-18 02:30 UTCEG score recompute
  11. 2026-09-18 02:30 UTCGHSA enrichment
  12. 2026-09-17 15:23 UTCEG score recompute
  13. 2026-09-17 14:34 UTCEG score recompute
  14. 2026-09-17 14:34 UTCMITRE cvelistV5first tracked

Frequently asked(5)

What is CVE-2026-92983?
CVE-2026-92983 is a high vulnerability published on September 17, 2026. InternLM LMDeploy through 0.17.0 in DistServe prefill/decode disaggregation mode fails to release scheduler sessions because the proxy uses user-facing session IDs instead of internal scheduler keys. Unauthenticated attackers can send completion requests to the proxy endpoint that accumulate…
When was CVE-2026-92983 disclosed?
CVE-2026-92983 was first published in the National Vulnerability Database on September 17, 2026, with the most recent update on September 18, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-92983 actively exploited?
CVE-2026-92983 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0% probability of exploitation in the next 30 days, which ranks it in the top 69.6% of all scored CVEs.
What is the CVSS score of CVE-2026-92983?
CVE-2026-92983 has a CVSS v3 base score of 7.5 (NVD).
How do I remediate CVE-2026-92983?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-92983, 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

Explore the affected products and dependency analysis for CVE-2026-92983

Explore →

Is Your Infrastructure Affected by CVE-2026-92983?

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

Start Free Scan →Browse All CVEs