CVE-2026-116181
vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows…
- Risk score
- 45/100
- CVSS
- 6.5 v3.1
- Exploit chance (30 days)
- 0.4%
- Published
- 25 Oct 2026
Open in the live forecast Today's forecast
What to know
- What it is
- vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 run…
- Affected
- See advisory
- Fix
- Upgrade the product to 0.29.0 or later.
- Exploitation
- No known exploitation
Why it is Yellow
- CVSS 6.5 medium
References
Original description
vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.
Last activity 25 Oct 2026. Patch Forecast updates every hour.