CVE-2026-90713Low· 3.3▾ TwilightPoC availableA security flaw has been discovered in vllm-project vLLM up to 0.29.0. The affected element is the function TiktokenTokenizer::new of the file rust/src/text/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipula…
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 18.2 · likelihood 0 · 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 Sep 15.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
Last analysed / modified upstream
0.2%
Exploit / PoC code exists
A security flaw has been discovered in vllm-project vLLM up to 0.29.0. The affected element is the function TiktokenTokenizer::new of the file rust/src/text/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipulation results in denial of service. The attack is only possible with local access. The exploit has been released to the public and may be used for attacks. The pull request to fix this issue awaits acceptance.
Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Field changes observed since this record was first indexed.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-92365Medium· 4.3A vulnerability was found in vllm-project vllm up to 0.29.0
CVE-2026-92220Medium· 5.3A vulnerability was found in vllm-project vLLM 0.26.0/0.27.0
CVE-2026-90878Medium· 4.3A vulnerability was determined in vllm-project vLLM up to 0.27.1
CVE-2026-69147Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-57173Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-5497High· 7.5vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to unbounded frame count processing in the `VideoMediaIO.load_base64()` method