Database/AI/ML frameworks & serving
NVIDIA OpenShell: unbounded chunked requests exhaust the inference-interception parser
Impact
OpenShell's inference-interception parser sets no limit on body size or chunk count for chunked requests. A sandboxed workload can tie it up with excessive parsing work. Because the scope is changed, the denial of service can reach beyond the attacker's own sandbox and may hit other sandboxes that share the interception path. There is no confidentiality or integrity impact.
Who can reach it
Low-privileged actor inside an OpenShell sandbox who can send inference requests. No user interaction needed.
What to do
Update NVIDIA OpenShell to the fixed release in NVIDIA product-security bulletin 5929. The record does not give a fixed version. Until then, watch the interception component's resource use and restart it if it is exhausted.
References
Related entries
- vLLM: mirrored multimodal cache desync lets a rejected request assert-kill the engine on reuseCVE-2026-105753 · vLLM MultiModalProcessorSenderCache / MultiModalReceiverCache (mirrored LRU cache)Medium
- vLLM: forged multimodal features on the disaggregated generate path kill EngineCore and poison encoder cacheCVE-2026-105754 · vLLM /inference/v1/generate (disaggregated scale-out: caller-supplied tensors, mm_hashes, mm_placeholders)Medium
- vLLM: unvalidated cache_salt raises an uncaught ValueError and terminates EngineCoreCVE-2026-105756 · vLLM OpenAI-compatible API (cache_salt validation with the LMCache-MP connector)Medium
- vLLM: structured-output request failures escape request scope and terminate the shared engineCVE-2026-105757 · vLLM structured-output path (grammar compilation, ngram_gpu speculative decoding, Rust frontend validation)Medium
- MLflow: unauthenticated scorer/invoke deserialization lets a caller drive outbound requests to internal hostsCVE-2026-115886 · MLflow scorer endpoints (Scorer.model_validate_json deserialization)Medium
- vLLM: unbounded chat-template rendering lets one request wedge or exhaust the serving processCVE-2026-115911 · vLLM OpenAI-compatible server (request-supplied Jinja chat template rendering)Medium
This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.