CVE-2026-114049Low· 3.7▾ SunlitvLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate…
▾ Sunlit zone — Low / medium · no exploitation signal
impact 20.4 · likelihood 0 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycled batch slots apply their token allowlist to victims' unrestricted requests.
vllm < 0.31.0Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-114052High· 7.5vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize mm_processor_kwargs
CVE-2026-114051High· 7.5vLLM before 0.31.0 Denial of Service via min_tokens in /inference/v1/generate
CVE-2026-114050High· 7.5vLLM before 0.31.0 Remote Engine Crash via Forged Multimodal UUID
CVE-2026-114054Medium· 6.5vLLM before 0.31.0 Cross-Request Cache Aliasing via EXIF ImageID and Prefix-Cache Keys
CVE-2026-114053High· 8.1vLLM 0.7.3 before 0.31.0 RCE via mm_processor_kwargs.code_revision
CVE-2026-114055High· 7.5vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs