Inference data disclosure and tampering via path misnormalization
Published Aug 25, 2026 · Updated Aug 25, 2026
Improper output encoding in NVIDIA OpenShell 0.0.33 and earlier allows local users to disclose or alter data through its inference proxy. The normalize_inference_path routine stripped the scheme and authority but preserved dot segments, allowing crafted paths to evade managed inference-route matching. A user able to issue requests from an OpenShell sandbox can reach ordinary egress handling instead of the intended managed model route, exposing or modifying inference traffic within permitted connectivity.
Summary
What happened
Improper output encoding in NVIDIA OpenShell 0.0.33 and earlier allows local users to disclose or alter data through its inference proxy. The normalize_inference_path routine stripped the scheme and authority but preserved dot segments, allowing crafted paths to evade managed inference-route matching. A user able to issue requests from an OpenShell sandbox can reach ordinary egress handling instead of the intended managed model route, exposing or modifying inference traffic within permitted connectivity.
The record
- CVE
- CVE-2026-65085
- Published
- Aug 25, 2026
- Updated
- Aug 25, 2026
- Vendor
- DPDK Project
- Product
- OpenShell
- Classifications
- CWE-116
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- Aug 25, 2026CVE publishedPublication date reported by the CVE source.
- Aug 25, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 to 0.0.33
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo