Lmsys Sglang: vulnerabilidades y CVE

SGLang through 0.5.20 in prefill/decode disaggregation mode fails to validate duplicate bootstrap_room fields in /generate requests with Mooncake KV transfer backend. Unauthenticated attackers can send concurrent…

SGLang contains a DoS vulnerability caused by missing input validation for AUX_DATA ZeroMQ control messages in the Decode worker, which enables an unauthenticated remote attacker with network reachability to the Decode…

SGLang's multimodal generation runtime is vulnerable to unauthenticated arbitrary code execution because the disaggregated-diffusion orchestrator's DiffusionServer binds an unauthenticated ZeroMQ ROUTER socket to a…

SGLang versions through 0.5.20 contain an unbounded memory allocation vulnerability in handle_staging_req() that fails to validate chunk_idx from ZMQ STAGING_REQ frames in prefill/decode disaggregation deployments.…

SGLang through 0.5.19 in prefill/decode disaggregation mode with Mooncake KV transfer backend fails to validate bootstrap_room values, allowing unbounded transfer state allocation. Unauthenticated attackers can reach…

SGLang through 0.5.19 in prefill/decode disaggregation mode contains an unauthenticated PUT /route endpoint on the prefill bootstrap service that allows attackers to poison the KV transfer routing table. Attackers can…

SGLang allows unauthenticated pickle deserialization through /update_weights_from_tensor when no auth keys are configured, and the SafeUnpickler policy can be bypassed because builtins.import and builtins.getattr are…

SGLang contains a model weight exfiltration vulnerability when no API keys are configured, as SGLang will expose two endpoints that allow a remote attacker to trigger distributed weight broadcasting using NCCL and then…

SGLang contains a credential leakage vulnerability in the /server_info endpoint, which will return API keys and SSL keyfile information when only the --admin-api-key is configured.

SGLang contains a RCE vulnerability when attempting to load model weights from a HuggingFace repository, specifically within the /update_weights_from_disk, where torch.load(..., weights_only=False) fallback enables…

SGLang contains an SSRF and local file read in the multimodal generation endpoint /v1/chat/completions due to unsanitized image_url, allowing access to internal metadata, secrets, and services.

SGLang contains an RCE vulnerability when the optional dumper subsystem is enabled, allowing for a sandbox escape when DUMPER_SERVER_PORT is set, enabling code execution on inference requests.

SGLang contains an unauthenticated RCE in /load_lora_adapter_from_tensors via bypass of SafeUnpickler’s incomplete denylist, allowing arbitrary command execution through crafted base64-encoded pickle payloads.

SGLang uses an expert-parallel backup subsystem that exposes a ZeroMQ PULL socket on a routable network interface that does not contain authentication or deserialization safeguards, allowing an attacker to provide a…

A vulnerability was determined in sgl-project SGLang up to 0.5.11. Affected by this vulnerability is the function data_hash of the component Cache Handler. This manipulation causes denial of service. The attack is…

A security vulnerability has been detected in SGLang 0.5.10.post1. Impacted is an unknown function of the file python/sglang/srt/lora/lora_manager.py of the component Inference HTTP Endpoint. Such manipulation of the…

SGLangs multimodal generation runtime is vulnerable to unauthenticated remote code execution when the --enable-custom-logit-processor option is enabled, as Python objects loaded via dill.loads() will be deserialized…

SGLangs multimodal generation runtime is vulnerable to an unauthenticated path traversal vulnerability, allowing an attacker to write arbitrary files anywhere the server process has write access, by including ../…

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.

A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function get_tokenizer of the file python/sglang/srt/utils/hf_transformers_utils.py of the component HuggingFace Transformer Handler. The…

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…

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…

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.

A security flaw has been discovered in lmsys sglang 0.4.6. Affected by this vulnerability is the function main of the file /update_weights_from_tensor. The manipulation of the argument serialized_named_tensors results…