{"catalog":"https://launchinyourcloud.com/api/v1/catalog.json","catalogRevision":"170de95bb7d832897d269051ad4500713acf96a62f3d01bc1d4e649679a56fde","kind":"listing","listing":{"advisories":[{"action":"Disable or isolate debug dumper endpoints and verify an upstream fix before treating a newer release as remediated.","conditions":"Requires dumper configuration access and a subsequent model execution reaching a dumper hook. In shared-API mode, an ordinary API key can suffice without a separate admin key; authentication configuration changes exposure.","id":"sglang-cve-2026-111391","listingIds":["sglang"],"reviewed":"2026-11-16","scope":"CVE record: SGLang 0.5.10–0.5.22. The open upstream report and reviewed v0.5.23 code do not establish a fixed release.","source":"https://cveawg.mitre.org/api/cve/CVE-2026-111391","summary":"CVE-2026-111391 identifies code execution in the debug dumper filter. Check the debug endpoint exposure and authentication boundary.","supportingSources":[{"title":"Upstream report and authentication conditions","url":"https://github.com/sgl-project/sglang/issues/44188"},{"title":"Reviewed v0.5.23 filter implementation","url":"https://github.com/sgl-project/sglang/blob/v0.5.23/python/sglang/srt/debug_utils/dumper.py#L1309-L1320"}],"title":"SGLang debug dumper code execution","type":"security-advisory"}],"architecture":"Customer-operated inference server and model weights on configured accelerator hosts","categories":["ai-inference-gateways","ai-tools"],"category":"AI inference \u0026 gateways","categoryFit":{"ai-inference-gateways":"Model-serving framework for LLM and multimodal inference; an inference runtime rather than a full multi-provider governance gateway.","ai-tools":"Customer-operated inference infrastructure for serving supported model weights."},"cloudEvidence":[{"clouds":["gcp"],"notes":"Google explicitly supports SGLang as an alternative model server in its customer-operated multi-cluster GKE inference architecture. The worked manifests use vLLM; SGLang requires its own deployment, serving port, metric mapping and compatible Endpoint Picker image. Review GPU/model requirements, licenses and resource availability.","reviewed":"2026-11-12","sourceType":"provider-guide","title":"SGLang compatibility with GKE Inference Gateway","url":"https://docs.cloud.google.com/kubernetes-engine/docs/how-to/setup-multicluster-inference-gateway","vendorSupport":"not-assessed"}],"cloudReviewed":"2026-11-12","clouds":["gcp"],"communityAcceptance":{"reviewed":"2026-11-10","sources":[{"title":"Release maintenance and contributor participation","url":"https://github.com/sgl-project/sglang/releases"},{"title":"Project and production-use context","url":"https://raw.githubusercontent.com/sgl-project/sglang/main/README.md"}],"summary":"The upstream release history documents hundreds of pull requests from many named contributors and sustained releases; its README describes production use across labs, platforms and enterprises."},"deploymentPaths":[{"boundary":"cloud-account","cloud":"gcp","controlPlane":"not-assessed","evidence":[0],"operator":"customer"}],"description":"Model-serving framework for running supported language and multimodal models on customer-controlled compute.","diligence":{"footprint":{"reviewed":"2026-11-20","scope":"Model and serving-configuration dependent; complete production footprint unresolved","source":"https://docs.sglang.ai/advanced_features/server_arguments.html","status":"inconclusive","summary":"The server configuration sizes model loading, quantization, parallelism, KV cache and admitted requests through memory controls such as mem-fraction-static. It does not establish one safe CPU/RAM/VRAM minimum. Select model, precision, context, concurrency and availability, then validate the chosen accelerator topology."},"iac":{"reviewed":"2026-11-14","scope":"Upstream self-hosted deployment; not a provider support or production-readiness certification","source":"https://docs.sglang.io/docs/get-started/install","status":"documented","summary":"The upstream installation guide supplies container, Compose and Kubernetes options for model serving. Match model/backend, accelerator drivers and selected image; examples do not establish a universal GPU or memory minimum."},"licensePricing":{"reviewed":"2026-11-20","scope":"Upstream core licence; commercial features, support and hosting priced separately","source":"https://raw.githubusercontent.com/sgl-project/sglang/main/LICENSE","status":"documented","summary":"The reviewed upstream core is Apache-2.0 licensed. Optional services, bundled dependencies, commercial distributions and support can have separate terms. This records the source licence, not an infrastructure or operating-cost estimate. Model weights and external model APIs require their own review."},"release":{"releasePublishedAt":"2026-11-02T22:14:10Z","releaseTag":"v0.5.23","reviewed":"2026-11-14","scope":"Upstream sgl-project/sglang release record; commercial editions and deployment packages may differ","source":"https://github.com/sgl-project/sglang/releases/tag/v0.5.23","status":"documented","summary":"The publisher-designated GitHub release checked was v0.5.23, published 2026-11-02. This is a release snapshot, not a promised cadence, support designation or approval to substitute it into a provider package."},"securityControls":{"reviewed":"2026-11-16","scope":"Debug dumper trust boundary and deployment precautions; not a blanket claim that all SGLang endpoints or all later releases are unauthenticated","source":"https://github.com/sgl-project/sglang/issues/44188","status":"documented","summary":"The reported shared-API dumper exposure requires DUMPER_SERVER_PORT=reuse and access to configure a filter followed by a model execution. Without a separate admin key, an ordinary API key can reach the route; without any API key, it can be anonymous. A configured admin key is required when present. Keep dumper/debug routes disabled or network-isolated. The CVE enumerates 0.5.10–0.5.22; retained filter code in 0.5.23 is not by itself a complete assessment of every authentication configuration.","supportingSources":[{"title":"Primary CVE record","url":"https://cveawg.mitre.org/api/cve/CVE-2026-111391"},{"title":"SGLang v0.5.23 shared dumper route and authentication level","url":"https://github.com/sgl-project/sglang/blob/v0.5.23/python/sglang/srt/entrypoints/http_server.py"},{"title":"SGLang v0.5.23 filter implementation","url":"https://github.com/sgl-project/sglang/blob/v0.5.23/python/sglang/srt/debug_utils/dumper.py#L1309-L1320"}]},"sso":{"reviewed":"2026-11-20","scope":"Upstream inference-server/API authentication; federation unresolved","source":"https://docs.sglang.ai/advanced_features/server_arguments.html","status":"inconclusive","summary":"Server arguments document inference and administrative API keys with separate endpoint rules. The reviewed upstream configuration does not establish SAML/OIDC login, user provisioning or a supported IdP integration. Confirm a gateway-based identity design instead of treating a static API key as SSO."}},"id":"sglang","infrastructure":["servers"],"infrastructureNotes":"Customer-operated inference server and model weights on configured accelerator hosts. This is a customer-operated server/container deployment; portability does not establish named cloud-provider support.","infrastructureReviewed":"2026-11-10","infrastructureSources":["https://docs.sglang.io/docs/get-started/install"],"install":"Install the package or use official containers; the reviewed primary installation path targets Linux with supported NVIDIA GPUs and compatible drivers.","installMethods":["docker","package"],"kind":"product","license":"Apache License 2.0 for upstream SGLang. Model weights and hardware/runtime dependencies have their own licenses.","licenseModel":"open-source","licenseModelNotes":"Apache License 2.0 for upstream SGLang. Model weights and hardware/runtime dependencies have their own licenses. This classification covers the reviewed upstream edition; external services and dependencies retain their own terms.","licenseModelSources":["https://raw.githubusercontent.com/sgl-project/sglang/main/LICENSE"],"licenseReviewed":"2026-11-10","model":"Fully in your account","modelLabel":"Customer-operated","name":"SGLang","notes":"Model downloads may require external registries and gated-model credentials. Pin compatible model/runtime/image versions and review model-specific permissions. Generic container instructions do not establish deployment badges for every hyperscaler. CVE-2026-111391 rates SGLang 0.5.10 through 0.5.22 critical (CVSS v4.0 9.2) for Python code execution through the debug dumper filter. The upstream report demonstrates the shared-API path with DUMPER_SERVER_PORT=reuse: an ordinary API-key holder can reach it when no separate admin API key is configured; access can be anonymous when no API key is configured. With an admin API key configured, that key is required. Exploitation also requires access to the dumper configuration and a subsequent model execution that reaches a dumper hook. Upstream issue #44188 remains open, and the v0.5.23 tag still contains the eval-based filter path even though that tag is outside the CVE record's enumerated affected range. Do not enable or expose the debug dumper endpoint; restrict it at the network layer and verify an upstream fix before treating a later version as remediated.","operations":"Customer manages accelerator capacity, model artifacts, runtime compatibility, endpoint access, including isolation of debug and dumper routes, monitoring, and upgrades.","publisher":false,"reviewed":"2026-11-16","sources":[{"title":"Official installation and runtime","url":"https://docs.sglang.io/docs/get-started/install"},{"title":"Upstream project and capabilities","url":"https://github.com/sgl-project/sglang"},{"title":"Current upstream license","url":"https://raw.githubusercontent.com/sgl-project/sglang/main/LICENSE"},{"title":"CVE-2026-111391 debug dumper filter code injection","url":"https://nvd.nist.gov/vuln/detail/CVE-2026-111391"},{"title":"Upstream SGLang dumper-filter RCE issue","url":"https://github.com/sgl-project/sglang/issues/44188"},{"title":"SGLang v0.5.23 debug dumper implementation","url":"https://github.com/sgl-project/sglang/blob/v0.5.23/python/sglang/srt/debug_utils/dumper.py#L1309-L1320"},{"title":"CVE-2026-111391 primary record and affected-version range","url":"https://cveawg.mitre.org/api/cve/CVE-2026-111391"}],"url":"https://launchinyourcloud.com/directory/sglang/","website":"https://sglang.io/"},"schemaVersion":1,"url":"https://launchinyourcloud.com/directory/sglang/"}