vLLM
vLLM 0.19.0 before 0.31.0 Resource Exhaustion via Request-Level num_frames
vLLM from 0.19.0 before 0.31.0 contains a resource exhaustion vulnerability that allows inference clients to bypass the server frame limit by setting media_io_kwargs.video.num_frames in chat completion requests. Attackers can supply num_frames=-1 or a large value with many base64 JPEG frames, forcing VideoMediaIO to decode all frames and np.stack them, causing memory exhaustion.
First public PoC
None yetno public PoC found
Public PoCs00 on GitHub
CVSS7.1high · scored by CNA · CWE-770
CISA KEV
Not listednot known exploited
Affected versions and mitigation
From the CVE record and the vendor's references.Affected
vllm-project vllm
- >= 0.19.0, < 0.31.0
Fixed in 0.31.0
Mitigation
Upgrade vllm to 0.31.0 or later.
References
- Vendor advisory github.com/vllm-project/vllm/security/advisori…
Timeline
Days relative to CVE publicationNo public PoC found yet; not in CISA KEV.
PoC repositories
Found on GitHub.No PoC repositories found yet.