vLLM 版本低于 0.28.0 在 和 端点中未对令牌 ID(token ID)的下界进行校验,这使得未认证的攻击者能够通过提交负的令牌 ID 使引擎崩溃。一个包含负令牌 ID 的请求会触发 CUDA 设备端的断言,从而污染 GPU 上下文,导致后续所有请求均会失败,直到进程重启。
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| vllm-project | vllm | < 0.28.0 |
affected |
0.28.0 |
unaffected |
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| vllm-project | vllm | 0 ~ 0.28.0 | - |
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2026-93840 | 3.7 LOW | vLLM before 0.29.0 Cross-Request Logits Corruption via allowed_token_ids |
| CVE-2026-93841 | 3.7 LOW | vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token |
No comments yet