vLLM是vLLM开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.8.0至0.9.0之前版本存在安全漏洞,该漏洞源于使用无效json_schema调用/v1/completions API可能导致服务器崩溃。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 | >= 0.8.0, < 0.9.0 | - |
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2025-48887 | 6.5 MEDIUM | vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerabil |
| CVE-2025-48944 | 6.5 MEDIUM | vLLM Tool Schema allows DoS via Malformed pattern and type Fields |
| CVE-2025-48943 | 6.5 MEDIUM | vLLM allows clients to crash the openai server with invalid regex |
No comments yet