Veille CVE

Semaine du 12 octobre au 18 octobre 2026

9 CVE

Critique 0 Élevée 6 Moyenne 3 Faible 0 Non évaluée 0 Exploitées (KEV) Tri : plus récentes « SGLang » ✕
  1. CVE-2026-111392 4.8 Moyenne

    sgl-project sglang

    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.

  2. CVE-2026-111391 8.1 Élevée

    sgl-project sglang

    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.

  3. CVE-2026-110809 4.3 Moyenne

    sgl-project SGLang

    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.

  4. CVE-2026-110807 4.3 Moyenne

    sgl-project SGLang

    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.

  5. CVE-2026-109229 7.5 Élevée

    sgl-project sglang

    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.

  6. CVE-2026-109228 7.5 Élevée

    sgl-project sglang

    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.

  7. CVE-2026-109227 7.5 Élevée

    sgl-project sglang

    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.

  8. CVE-2026-109226 7.5 Élevée

    sgl-project sglang

    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.

  9. CVE-2026-109225 7.5 Élevée

    sgl-project sglang

    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.