CVE-2026-34755
vLLM is an inference and serving engine for large language models …
vLLM is an inference and serving engine for large language models (LLMs). From 0.7.0 to before 0.19.0, the VideoMediaIO.load_base64() method at vllm/multimodal/media/video.py splits video/jpeg data URLs by comma to extract individual JPEG frames, but does not enforce a frame count limit. The num_frames parameter (default: 32), which is enforced by the load_bytes() code path, is completely bypassed in the video/jpeg base64 path. An attacker can send a single API request containing thousands of comma-separated base64-encoded JPEG frames, causing the server to decode all frames into memory and crash with OOM. This vulnerability is fixed in 0.19.0.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-pq5c-rjhq-qp7p
- github.com/vllm-project/vllm/pull/38636
- github.com/vllm-project/vllm/commit/58ee61422169ce17e08248f8efa1e9df434fe395
- github.com/advisories/GHSA-pq5c-rjhq-qp7p
- nvd.nist.gov/vuln/detail/CVE-2026-34755
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-144.yaml
- access.redhat.com/security/cve/CVE-2026-34755
- bugzilla.redhat.com/show_bug.cgi?id=2455403
- nvd.nist.gov/vuln/detail/CVE-2026-34755
- cve.org/CVERecord?id=CVE-2026-34755
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.