CVE-2026-111160
LightLLM through 1.2.0 contains a denial of service vulnerability that allows unauthenticated…
- Risk score
- 57/100
- CVSS
- 7.5 v3.1
- Exploit chance (30 days)
- 0.4%
- Published
- 15 Oct 2026
Open in the live forecast Today's forecast
What to know
- What it is
- 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, kil…
- Affected
- See advisory
- Fix
- Apply the vendor's security update; see the linked advisory.
- Exploitation
- No known exploitation
Why it is Yellow
- CVSS 7.5 high
- Remotely exploitable without logging in
References
- https://github.com/ModelTC/LightLLM
- 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://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-dos-via-pd-kv-trans-params-deserialization
Original 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.
Last activity 15 Oct 2026. Patch Forecast updates every hour.