vLLM before 0.31.0 Denial of Service via min_tokens in /inference/v1/generate
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| vllm-project | vllm | unaffected |
|
No data.
| Vendor | Product | Versions | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Vllm | Vllm |
|
||||||||||||
| Vllm-project | Vllm |
|
No CVSS v3.0
No CVSS v2
This CVE is not in the KEV list.
Exploit prediction score: < 1% (0.383% probability within 30 days)
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
ssvc
|
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Vllm-project
Vllm-project vllm |
|
| Vendors & Products |
Vllm-project
Vllm-project vllm |
|
| References |
| |
| Metrics |
threat_severity
|
threat_severity
|
| Type | Values Removed | Values Added |
|---|---|---|
| Description | vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/generate requests with a null max_tokens, so the EngineCore input thread later dies on an uncaught VLLMValidationError while /health still returns 200. Unauthenticated remote attackers can send one request with an oversized min_tokens to hang all subsequent generation requests until manual restart. | |
| Title | vLLM before 0.31.0 Denial of Service via min_tokens in /inference/v1/generate | |
| First Time appeared |
Vllm
Vllm vllm |
|
| Weaknesses | CWE-248 | |
| CPEs | cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* | |
| Vendors & Products |
Vllm
Vllm vllm |
|
| References |
| |
| Metrics |
cvssV3_1
|