CVE-2026-34760High· 7.1▾ TwilightvLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing (to_mono), while the international standard ITU-R BS.775-4 sp…
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 39.1 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Jul 31.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via OSV
Last analysed / modified upstream
0.3%
0.3% → 0.5%
vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before version 0.18.0, Librosa defaults to using numpy.mean for mono downmixing (to_mono), while the international standard ITU-R BS.775-4 specifies a weighted downmixing algorithm. This discrepancy results in inconsistency between audio heard by humans (e.g., through headphones/regular speakers) and audio processed by AI models (Which infra via Librosa, such as vllm, transformer). This issue has been patched in version 0.18.0.
vllm >= 0.5.5, < 0.18.0Upgrade to a patched release:
vllm 0.18.0Connected by shared product, vendor, weakness, or advisory.
CVE-2026-114050Medium· 6.5vLLM: Forged multimodal UUID + P0/P1 processor-cache eviction drift: unauthenticated remote crash of the whole vLLM engine
CVE-2026-114055High· 7.5vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs
CVE-2026-105922Medium· 4.3A security flaw has been discovered in vllm-project vLLM up to 0.31.0
CVE-2026-105760Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-105759Medium· 5.9vLLM is an inference and serving engine for large language models
CVE-2026-105757Medium· 6.5vLLM is an inference and serving engine for large language models