GPU VulnDB

Database/AI/ML frameworks & serving

NVIDIA OpenShell: unbounded chunked requests exhaust the inference-interception parser

CVSS 6.5CVE-2026-100982AI/ML frameworks & servingcurated

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

All AI/ML frameworks & serving entries

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.