
Signal is active with 1 mentions in latest observed window
Recommended action window: Monitor and triage in normal cycle
NVD description
vLLM from 0.28.0 before 0.33.0 contains an improper input validation vulnerability that allows unauthenticated attackers to crash the shared EngineCore by sending out-of-range prompt token ids when served with --skip-tokenizer-init. Attackers can submit a large positive token id to /v1/completions, /v1/embeddings, or /pooling, bypassing the tokenizer-gated vocab check and causing a fatal embedding index error that denies service to all tenants.
Priority
LOW
Exploitation
NONE
PoC
NONE
Patch
NONE
Momentum
NONE

🚨 HIGH - Two Unauthenticated Denial-of-Service Flaws in vLLM Inference Engine (CVE-2026-130685 & CVE-2026-130686) The vLLM project has released version 0.33.0 addressing two high-severity, unauthenticated remote Denial-of-Service (DoS) vulnerabilities affecting LLM inference deployments: • CVE-2026-130685: Improper input validation when served with --skip-tokenizer-init allows attackers to submit out-of-range prompt token IDs to /v1/completions, /v1/embeddings, or /pooling - bypassing vocab checks and crashing the shared EngineCore across all tenants. • CVE-2026-130686: Missing request-wide media budgets allow attackers to submit numerous remote image URLs in a single compact request to /v1/messages or /v1/responses, forcing image downloads/decoding before prompt-length checks and exhausting memory, CPU, and connections. 👉 Affected / Remediation: Affects vLLM 0.28.0 prior to 0.33.0 (CVE-2026-130685) and 0.6.0 prior to 0.33.0 (CVE-2026-130686). Upgrade immediately to vLLM 0.33.0 or later, and avoid exposing vLLM APIs directly to untrusted networks without authentication and rate limiting.