vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct

Summary

vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mm_processor_kwargs value in an unbounded dictionary. Unauthenticated attackers can send distinct or oversized mel_config values to the /tokenize endpoint, which bypasses --api-key, to exhaust host memory and crash the API process.

Remediation

1. Inventory every Vllm Vllm deployment, including staging.
2. Upgrade Vllm Vllm to 0.31.0.
3. Confirm the running version after the upgrade.

References

• Advisoryhttps://github.com/vllm-project/vllm/security/advisories/GHSA-823j-m4cj-hmjf
• Advisoryhttps://www.vulncheck.com/advisories/vllm-0.25.0-before-0.31.0-moss-audio-memory-exhaustion-via-tokenize-mm-processor-kwargs