LightLLM <= 1.1.0 PD Mode Unsafe Deserialization RCE
28Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 9.3epss 0.8%
exploitation probability
0.8%top 44% of all CVEs
observed exploitation
nono source reports it
LightLLM version 1.1.0 and prior contain an unauthenticated remote code execution vulnerability in PD (prefill-decode) disaggregation mode. The PD master node exposes WebSocket endpoints that receive binary frames and pass the data directly to pickle.loads() without authentication or validation. A remote attacker who can reach the PD master can send a crafted payload to achieve arbitrary code execution.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Affected products
ModelTC · LightLLMReferences
https://chocapikk.com/posts/2026/lightllm-pickle-rce/https://github.com/ModelTC/lightllm/blob/a27dfc88c2144ed51a6e160b6fbe20aad66c8fe0/lightllm/server/api_http.py#L310https://github.com/ModelTC/lightllm/blob/a27dfc88c2144ed51a6e160b6fbe20aad66c8fe0/lightllm/server/api_http.py#L331https://github.com/ModelTC/LightLLM/issues/1213https://lightllm-en.readthedocs.io/en/latest/index.htmlhttps://www.vulncheck.com/advisories/lightllm-pd-mode-unsafe-deserialization-rce