CVE-2026-100652
Vllm: improper input validation
- Risk score
- 61/100
- CVSS
- 7.5 v3.1
- Exploit chance (30 days)
- 0.4%
- Published
- 26 Sep 2026
Open in the live forecast Today's forecast
What to know
- What it is
- vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA ten…
- Affected
- Vllm
- Fix
- Apply the vendor's security update; see the linked advisory.
- Exploitation
- Public proof of concept
Why it is Amber
- CVSS 7.5 high
- Public exploit or proof of concept referenced
- Remotely exploitable without logging in
References
Original description
vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.
Last activity 26 Sep 2026. Patch Forecast updates every hour.