mittel5.3
CVE-2025-71379
vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities.
Auswirkung
vLLM versions >= 0.6.3 and < 0.9.0 contain multiple regular expression denial of service (ReDoS) vulnerabilities. Several regex patterns — in vllm/lora/utils.py, the phi4mini tool parser, and the OpenAI-compatible serving chat endpoint — are susceptible to catastrophic backtracking. An attacker submitting crafted input with nested or repeated structures can trigger severe CPU consumption and performance degradation, resulting in denial of service.
Ein Angreifer kann die Lücke über das Netzwerk ausnutzen, mit einem normalen Benutzerkonto, ohne Zutun eines Nutzers. Bei Erfolg: geringes Risiko für Ausfälle.
Betroffene Pakete
| Ökosystem | Paket | Betroffen | Behoben in |
|---|---|---|---|
| pip | vllm | >= 0.6.3, < 0.9.0 | 0.9.0 |
Betroffene Produkte
| Hersteller | Produkt | Betroffene Versionen |
|---|---|---|
| Vllm | Vllm | ab 0.6.3 vor 0.9.0 |
| Vllm-project | Vllm | ab 0.6.3 vor 0.9.0 |
Schwachstellenklasse
Referenzen
- NVD-Eintrag
- CVE.org-Eintrag
- GitHub-Advisory
- https://github.com/advisories/GHSA-vfm7-4h43-gp6m
- https://github.com/vllm-project/vllm/security/advisories/GHSA-j828-28rj-hfhp
- https://nvd.nist.gov/vuln/detail/CVE-2025-71379
- https://www.vulncheck.com/advisories/vllm-regular-expression-denial-of-service-in-multiple-components