Lmsys ≫ Sglang

SGLangs multimodal generation runtime scheduler's ROUTER socket binds to 0.0.0.0 by default and contains a sink that calls pickle.loads() on incoming messages, enabling RCE when exposed to the internet.

SGLang's reranking endpoint (/v1/rerank) achieves Remote Code Execution (RCE) when a model file containing a malcious tokenizer.chat_template is loaded, as the Jinja2 chat templates are rendered using an unsandboxed jinja2.Environment().

SGLangs `replay_request_dump.py` contains an insecure pickle.load() without validation and proper deserialization. An attacker can take advantage of this by providing a malicious .pkl file, which will execute the attackers code on the device running ...

SGLang' encoder parallel disaggregation system is vulnerable to unauthenticated remote code execution through the disaggregation module, which deserializes untrusted data using pickle.loads() without authentication.

SGLang's multimodal generation module is vulnerable to unauthenticated remote code execution through the ZMQ broker, which deserializes untrusted data using pickle.loads() without authentication.