VulnSocial

CVE-2026-94623

LOWCVSS 8.7 · HIGH

Signal is active with 1 mentions in latest observed window

Immediate actions

  • Track advisory updates for patch or workaround availability

Recommended action window: Monitor and triage in normal cycle

NVD description

vLLM through 0.29.0 contains a denial of service vulnerability in the NIXL connector's prefix caching implementation that fails to properly validate block counts across multi-prompt completion requests in prefill/decode disaggregated deployments. Attackers can trigger an assertion failure in NixlBaseConnectorWorker._apply_prefix_caching by submitting completion requests with multiple prompts of varying lengths, causing the decode worker to terminate and become unavailable until restarted.

Back to dashboard
0.0/ 10 priority

Sources & remediation

Other references
Weakness type (CWE)
CWE-617

Priority

LOW

Exploitation

NONE

PoC

NONE

Patch

NONE

Momentum

NONE

Threat summary

  • 1 mentions across 1 observed day

What's happening

  • 1 total mentions across 1 day

Deep dive

Activity timeline1 mentions / 1d
00111Mentions · 2026-09-22: 109-22
Referenced assets1 URL
By indicator
Full discourse1 post
  • ThreatAft@ThreatAft

    🚨 vLLM DoS CLUSTER — 5 × CVSS 7.5 One crafted request crashes the shared inference worker. Every client loses service. • CVE-2026-94622 — NIXL metadata • CVE-2026-94623 — Prefix caching → https://threataft.com/articles/vllm-dos-cluster-five-memory-exhaustion-cves #vLLM #CVE #LLM #PatchNow #CyberSecurity #ThreatIntel

    0000045
    43 followersView on X

Explore more

Back to dashboard