Vulnerability · Published Feb 17, 2026 · Assigned by VulnCheck
CVE-2026-26220LightLLM <= 1.1.0 PD Mode Unsafe Deserialization RCE
Critical 9.3
In plain English
A critical-severity unsafe deserialization in LightLLM from ModelTC. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 1.0% (higher than 62% of all known vulnerabilities).
Official description
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.
Affected products (as reported)
Weakness: CWE-502 · Vector: 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
References
- https://chocapikk.com/posts/2026/lightllm-pickle-rce/ technical-description, exploit
- https://github.com/ModelTC/LightLLM/issues/1213 issue-tracking
- https://lightllm-en.readthedocs.io/en/latest/index.html product
- https://github.com/ModelTC/lightllm/blob/a27dfc88c2144ed51a6e160b6fbe20aad66c8fe0/lightllm/server/api_http.py#L310 product
- https://github.com/ModelTC/lightllm/blob/a27dfc88c2144ed51a6e160b6fbe20aad66c8fe0/lightllm/server/api_http.py#L331 product
- https://www.vulncheck.com/advisories/lightllm-pd-mode-unsafe-deserialization-rce third-party-advisory