CVE-2026-5497
CVE-2026-5497 · Unbounded Frame Count in video/jpeg Base64 Data URL Processing Leads to OOM DoS in vllm-project/vllm
Cette page présente des faits issus de sources publiques. Consultez l’avis original avant toute mise à jour.
vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method. When processing `video/jpeg` data URLs, the method splits the base64 data string on commas to extract individual JPEG frames without enforcing a frame count limit. An attacker can exploit this by crafting a single API request containing thousands of comma-separated base64-encoded JPEG frames in a data URL, causing the server to decode all frames into memory and crash due to excessive memory consumption. This vulnerability is reachable via the OpenAI-compatible chat completions API and does not require authentication.
CVSS 7.5 · Élevée · EPSS 0,5% · Correctif disponible
- Publication
- Mise à jour
Pile logicielle: python
Produits et versions concernés
vllm-project/vllm
- Versions du logiciel
- ≥ unspecified, < 0.19.0: Concernée (custom)
Mettez à jour vers 0.19.0
vllm PyPI
- Versions du logiciel
- 0.10.0
- 0.10.1
- 0.10.1.1
- 0.10.2
- 0.11.0
- 0.11.1
- 0.11.2
- 0.12.0
- 0.13.0
- 0.14.0
- 0.14.1
- 0.15.0
- 0.15.1
- 0.16.0
- 0.17.0
- 0.17.1
- 0.18.0
- 0.18.1
- 0.8.0
- 0.8.1
- 0.8.2
- 0.8.3
- 0.8.4
- 0.8.5
- 0.8.5.post1
- 0.9.0
- 0.9.0.1
- 0.9.1
- 0.9.2
- Plages de versions concernées
- ECOSYSTEM: ≥ 0.8.0, < 0.19.0
Mettez à jour vers 0.19.0
Sources originales
- https://huntr.com/bounties/7bd92629-b396-4449-8f88-6c0092530eb4
- https://github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395
- https://access.redhat.com/security/cve/CVE-2026-5497
- https://bugzilla.redhat.com/show_bug.cgi?id=2487813
- https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-5497.json
- https://nvd.nist.gov/vuln/detail/CVE-2026-5497