SGLang through 0.5.22 with the Mooncake disaggregation backend accepts unauthenticated decode registration messages on the Prefill rank ZMQ PULL socket, allowing denial of service. Network-adjacent attackers can send many registrations with unique mooncake_session_id values and large nested-buffer frames to exhaust Prefill memory until the scheduler is OOM-killed.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
A vulnerability was identified in sgl-project SGLang up to 0.5.19. This impacts the function Scheduler.expert_distribution_handle of the file python/sglang/srt/eplb/expert_distribution.py of the component Expert-Distribution Recording Endpoint. Such manipulation leads to denial of service. It is possible to launch the attack remotely. The exploit is publicly available and might be used. The pull request to fix this issue awaits acceptance.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
SGLang through 0.5.22 with the Mooncake disaggregation backend contains an uncontrolled memory allocation vulnerability in handle_staging_rsp() that lets unauthenticated network-adjacent attackers exhaust Prefill memory. Attackers can obtain the rank address from the /route endpoint and send STAGING_RSP messages with huge chunk_idx values under fresh room IDs, causing the scheduler to be OOM-killed.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
A security flaw has been discovered in sgl-project SGLang up to 0.5.19. Affected is the function WeightExporter.send_weights_to_remote_instance of the file python/sglang/srt/model_executor/model_runner_components/weight_exporter.py of the component Weight Exporter. Performing a manipulation of the argument group_name results in denial of service. The attack can be initiated remotely. The exploit has been released to the public and may be used for attacks. The pull request to fix this issue awaits acceptance.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
SGLang through 0.5.22 contains a denial of service vulnerability that allows API clients to abort other users' in-flight generation requests by supplying a short client-controlled rid. Attackers can submit streaming /generate requests with single hex character rids and disconnect, triggering prefix-matching abort logic that terminates all other clients' requests.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
SGLang through 0.5.21 contains an unbounded memory allocation vulnerability in preprocess_video in qwen_vl.py that decodes frames at full source resolution before applying max_pixels limits. Remote attackers can submit high-resolution videos to /v1/chat/completions on Qwen-VL deployments, and concurrent requests exhaust worker memory causing denial of service.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
SGLang through 0.5.21 trusts caller-supplied mm_hashes values as the multimodal prefix-cache key, allowing remote attackers to poison cached KV entries across requests. Attackers can send a different image under a known or predicted hash via /generate to disclose another request's image content or corrupt victims' responses.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
SGLang 0.5.10 through 0.5.22 contains a code injection vulnerability in _evaluate_filter() that allows remote attackers to execute Python code by escaping the eval() sandbox through re.search __globals__. Attackers can send a crafted filter expression to the unauthenticated /dumper/configure endpoint when DUMPER_SERVER_PORT is set, running code in the scheduler process on the next forward pass.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
A security vulnerability has been detected in sgl-project SGLang up to 0.5.19. Affected by this issue is the function Session.create_req of the file python/sglang/srt/session/session_controller.py of the component Session Cleanup. Such manipulation leads to denial of service. The attack may be performed from remote. The exploit has been disclosed publicly and may be used. The pull request to fix this issue awaits acceptance.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
A weakness has been identified in sgl-project SGLang up to 0.5.19. Affected by this vulnerability is an unknown functionality of the file python/sglang/srt/managers/io_struct.py of the component generate Endpoint. This manipulation of the argument session_params causes denial of service. The attack is possible to be carried out remotely. The exploit has been made available to the public and could be used for attacks. The project was informed of the problem early through an issue report but has not responded yet.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
SGLang through 0.5.21 contains a resource budget bypass vulnerability that allows remote attackers to override GLM-V video processing limits by supplying fps, max_frames, max_tokens_per_frame and max_image_tokens in the video_url object. Attackers can set these values arbitrarily high so glm4v.py decodes every frame of high-resolution video at full size, exhausting worker memory and denying service.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
SGLang through 0.5.21 contains a decompression amplification vulnerability in load_audio that allows remote attackers to exhaust memory by submitting highly compressed audio decoded without duration or sample limits. Attackers can supply small FLAC-encoded silence files through audio_url or audio_data inputs that expand into massive PCM buffers, exhausting worker memory and CPU for denial of service.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
SGLang through 0.5.21 contains an unbounded memory allocation vulnerability that allows unauthenticated remote attackers to exhaust memory by uploading oversized files to /v1/audio/transcriptions. Attackers can send concurrent large multipart uploads, which are fully read into memory before validation, to crash the HTTP/tokenizer worker and deny service.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
SGLang through 0.5.21 contains a denial of service vulnerability that disables Pillow decompression bomb protection process-wide by setting Image.MAX_IMAGE_PIXELS to None in NanoNemotronVLImageProcessor. Remote attackers can submit small, highly compressed images with huge dimensions to the generic image loader, exhausting worker memory during decoding.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
SGLang contains an arbitrary code execution vulnerability caused by the ZMQ message decoder unconditionally deserializing PickleWrapper payloads via pickle.loads() in _maybe_unwrap_pickle without type allowlisting or authentication; this vulnerability persists via the msgpack path even when SGLANG_USE_PICKLE_IPC is disabled, and becomes remotely exploitable if data-parallel attention is enabled with a non-loopback --dist-init-addr setting.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
A vulnerability has been found in sgl-project sglang up to 0.5.21. This issue affects the function server_info of the file python/sglang/srt/entrypoints/http_server.py of the component HTTP Endpoint. Such manipulation of the argument api_key leads to cleartext transmission of sensitive information. It is possible to launch the attack remotely. Attacks of this nature are highly complex. The exploitability is assessed as difficult. The exploit has been disclosed to the public and may be used. The pull request to fix this issue awaits acceptance.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
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 requests with identical bootstrap_room values to crash scheduler processes or hang other users' requests until transfer timeout.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
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. Attackers with access to the decode engine's internal ZMQ rank port can send a frame with an extremely large chunk_idx value, causing the scheduler to allocate memory until the system runs out and terminates the process.
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
