CVE-2026-105759Medium· 5.9▾ TwilightPoC availablevLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An una…
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 32.5 · likelihood 0.1 · exploitation 12
A public proof-of-concept already exists for this vulnerability — see Exploit availability below.
Stakeholder-Specific Vulnerability Categorization from CISA's ADP record at CVE.org: whether exploitation is observed, whether an attack can be automated, and how much of the system is at stake.
Exploit-prediction probability, daily snapshots since Oct 7.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
Exploit / PoC code exists
0.3%
Last analysed / modified upstream
0.3% → 0.4%
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus's Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.
vllm < 0.30.0Upgrade past the affected range:
vllm 0.30.0Affected packages:
vllm < 0.30.0Patched in:
vllm 0.30.0Source: https://osv.dev/vulnerability/PYSEC-2026-4325
Field changes observed since this record was first indexed.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-105760Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-100650Medium· 6.5vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-p…
CVE-2026-69147Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-114055High· 7.5vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs
CVE-2026-105758Medium· 5.3vLLM is an inference and serving engine for large language models
CVE-2026-71486Medium· 4.3vLLM is an inference and serving engine for large language models