mittel6.5
CVE-2026-22773
vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions
Auswirkung
vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination. This issue has been patched in version 0.12.0.
Ein Angreifer kann die Lücke über das Netzwerk ausnutzen, mit einem normalen Benutzerkonto, ohne Zutun eines Nutzers. Bei Erfolg: hohes Risiko für Ausfälle.
Betroffene Pakete
| Ökosystem | Paket | Betroffen | Behoben in |
|---|---|---|---|
| pip | vllm | >= 0.6.4, < 0.12.0 | 0.12.0 |
Betroffene Produkte · Vllm
| Produkt | Betroffene Versionen |
|---|---|
| Vllm | ab 0.6.4 vor 0.12.0 |
Schwachstellenklasse
Referenzen
- NVD-Eintrag
- CVE.org-Eintrag
- GitHub-Advisory
- https://github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qr
- https://github.com/advisories/GHSA-grg2-63fw-f2qr
- https://nvd.nist.gov/vuln/detail/CVE-2026-22773
- https://github.com/vllm-project/vllm/pull/29881
- https://github.com/vllm-project/vllm/commit/0ec84221718d920c3f46da879cc354f94b8fb59e
- https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-143.yaml