🎯 CVE-2025-62164 HIGH 8.8 🔥 EPSS 92% 🧪 PoC 🇪🇺 EUVD
📄 .md Alle CVEs anzeigen ✕

CVE-2025-62164 | vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse

vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse tensor integrity checks are disabled by default. As a result, maliciously crafted tensors can bypass internal bounds checks and trigger an out-of-bounds memory write during the call to to_dense(). This memory corruption can crash vLLM and potentially lead to code execution on the server hosting vLLM. This issue has been patched in version 0.11.1.

Klassifikation & Betroffenheit:
vllm-project vllm 0.10.2, < 0.11.1
Improper Restriction of Operations within the Bounds of a Memory Buffer 🎯 High

The product performs operations on a memory buffer, but it reads from or writes to a memory location outside the buffer's intended boundary. This may result in read or write operations on unexpected memory locations that could be linked to other variables, data structures, or internal program data.

🛡️ Empfohlene Mitigation: Use a language that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid. For example, many languages that perform their own memory management, such as Java and Perl, are not subject to buffer overflows. Other languages, such as Ada and C#, typically provide overflow prot…
Vollständige Definition bei MITRE ➔
🩹 Patch verfügbar (OSV):
🩹 439368496db48d8f992ba8c606a0c0b1eebbfa69 (Commit) 🩹 58fab50d82838d5014f4a14d991fdb9352c9c84b (Commit)
📚 Referenzen & Quellen:
Ausnutzungs-Zeitleiste:
CVSS-Vektor-Analyse: 8.8
AV · Angriffsvektor Netzwerk
AC · Komplexität Gering
PR · Privilegien Gering
UI · Interaktion Keine
S · Scope Unverändert
C · Vertraulichkeit Hoch
I · Integrität Hoch
A · Verfügbarkeit Hoch
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Veröffentlicht:21.11.2025
Aktualisiert:24.11.2025 18:12
Assigner (CNA):GitHub_M
EUVD-ID:EUVD-2025-198314
CWE-119: Memory Corruption ✓ Offizieller Patch / Advisory verfügbar
💡 Gegenmaßnahme: Sicherheits-Update des Herstellers zeitnah einspielen und Netzwerksegmentierung prüfen.
🔴 Live Security Advisory & EPSS Exploit Radar

Zero-Day & Vulnerability Intelligence Hub

Echtzeit-Tracking mit EPSS Exploit-Wahrscheinlichkeiten, Angriffsvektor-Decodern und KI-Patch-Anleitungen.

354k+ 🇪🇺 EUVD-Datenbank
0 🔴 Critical im Radar
0 ⚠️ CISA KEV
0 🔓 Aktiv ausgenutzt
1 🧪 PoC verfügbar
📊 Historien-Charts — Criticals-Trend · Vendors · EPSS-Verteilung
🔴 Criticals pro Monat (12 M) 2025-09: 237 2025-10: 316 2025-11: 257 2025-12: 426 2026-01: 431 2026-02: 418 2026-03: 652 2026-04: 574 2026-05: 683 2026-06: 942 2026-07: 1333 2026-08: 1329 7.598 Criticals gesamt
🏢 Top-Vendor-Veröffentlichungen (6 M) Adobe Apple Google Linux Microsoft Oracle Corporation
● Adobe ● Apple ● Google ● Linux ● Microsoft ● Oracle
📈 EPSS-Verteilung (Messungen)
Tier2026-08-292026-09-06
≥90 %40
≥50 %40
≥10 %30
<10 %304300
📈 EPSS-Riser (7 Tage) CVE-2023-29073 ↑ 0.1 %
Frühindikator · FIRST.org
Datenquellen & Methodik: Primärquelle ist die EUVD der ENISA (laufender Datenbank-Sync, alle 15 Minuten), abgeglichen mit dem CISA-KEV-Katalog und der NVD — Detail-Dossiers reichern fehlende Felder live per NVD an — mit Fallback auf CIRCL vulnerability-lookup (EU/Non-Profit, aggregiert CVE-, GitHub- und OSV-Advisories). Der CISA-KEV-Katalog (Known Exploited Vulnerabilities, ~1.700 aktiv ausgenutzte Schwachstellen) wird bei jedem Sync vollständig neu geladen und kreuzreferenziert — filterbar über die KEV-Pille. CVSS 3.1 wird nach Ampel-Logik aus Verteidigersicht dekodiert; EPSS bezeichnet die 30-Tage-Exploit-Wahrscheinlichkeit (FIRST.org).
🇪🇺 ENISA EUVD 🇺🇸 NVD ⚠️ CISA KEV ⚡ EPSS
Ökosystem & Hersteller Bedrohungs-Matrix:
vllm-project 1
Schweregrad & Status:
Hersteller (Datenbank-weit, 90.597 Einträge):
Quelle:
Schwachstellen-Kategorie (CWE):
🔍
8.8 HIGH
🇪🇺 EUVD
EPSS 92%
CVE-2025-62164 🌐 Netzwerk (Remote) 🔑 Geringe Nutzerrechte nötig
🧪 vllm-project

CVE-2025-62164 | vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse

vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists

CWE-119: Memory Corruption ✓ Offizieller Patch / Advisory verfügbar
💡 Gegenmaßnahme: Sicherheits-Update des Herstellers zeitnah einspielen und Netzwerksegmentierung prüfen.