Description
LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated attackers to crash the inference worker by supplying the internal pd_kv_trans_params field to the /generate endpoint. Attackers can send a single request whose parameters cause pickle.loads to fail in InferSamplingParams, killing the inference thread while /health stays up and all later requests hang until restart.
Affected products
Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.
ModelTC LightLLM
Default version status: unaffected
0 to ≤ 1.2.0affected
pkg:github/ModelTC/lightllmReferences
- https://github.com/ModelTC/LightLLM/issues/1629 ↗
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/api_lightllm.py#L37-L43 ↗
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/core/objs/sampling_params.py#L356-L357 ↗
- https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/router/model_infer/infer_batch.py#L484-L485 ↗
- https://github.com/ModelTC/LightLLM ↗
- https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-dos-via-pd-kv-trans-params-deserialization ↗