EUVD-2026-72937
GHSA-rmxr-g66j-gfhg
Severity by source
AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Network-exposed inference server, no auth required, pure availability-only DoS - vendor vector is accurate and independently supportable.
Primary rating from Vendor (nvidia).
CVSS VectorVendor: nvidia
Lifecycle Timeline
2DescriptionCVE.org
NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker could cause excessive iteration. A successful exploit of this vulnerability might lead to denial of service.
AnalysisAI
Denial of service in NVIDIA Triton Inference Server for Linux allows unauthenticated remote attackers to exhaust server resources via a crafted request that triggers excessive iteration. All tracked versions under the wildcard CPE are potentially affected, and the vulnerability is network-reachable with no authentication or user interaction required per the CVSS:3.1/AV:N/AC:L/PR:N/UI:N vector. …
Unlock full vulnerability intelligence
- Risk assessment & exploitation conditions
- Attack chain visualization
- Remediation with exact patch versions
- Threat intelligence from 22 sources
- Personal watchlist & email alerts
Free forever · No credit card required
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata
Vulnerability AssessmentAI
| Exploitation | No special configuration or authentication is required - exploitation is possible against any default-configured Triton Inference Server for Linux instance with its HTTP or gRPC inference endpoint network-reachable (unauthenticated per PR:N). … Additional conditions and limiting factors are described in the full assessment. |
| Risk Assessment | The CVSS 7.5 score with AV:N/AC:L/PR:N/UI:N reflects a straightforward unauthenticated network-reachable DoS - a significant operational risk for any deployment where Triton's HTTP or gRPC ports are internet-facing or accessible from untrusted networks. … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in. |
| Exploit Scenario | Full exploit scenario with step-by-step reproduction available after sign-in. |
| Remediation | Consult the NVIDIA Product Security advisory at https://github.com/NVIDIA/product-security/tree/main/2026/5875 to identify the patched version and apply the vendor-released update as the primary remediation step; a specific fix version is not independently confirmed from the available structured data. … Detailed patch versions, workarounds, and compensating controls in full report. |
Recommended ActionAI
Within 24 hours, inventory all NVIDIA Triton Inference Server deployments and assess network exposure, prioritizing production systems. …
Sign in for detailed remediation steps and compensating controls.
Threat intelligence, references, and detailed analysis are available after sign-in.
More in Triton Inference Server
View allAuthentication bypass in NVIDIA Triton Inference Server allows unauthenticated remote attackers to reach protected funct
Path traversal in NVIDIA Triton Inference Server for Linux (CWE-22) lets remote attackers manipulate file paths to reach
Authentication bypass in NVIDIA Triton Inference Server allows remote unauthenticated attackers to circumvent access con
Integer overflow in the DALI backend of NVIDIA Triton Inference Server allows authenticated remote attackers to trigger
Out-of-bounds read in the DALI backend of NVIDIA Triton Inference Server allows authenticated remote attackers to trigge
NVIDIA Triton Inference Server for Linux contains a vulnerability where a user can set the logging location to an arbitr
NVIDIA Triton Inference Server for Linux contains a vulnerability in the tracing API, where a user can corrupt system fi
NVIDIA Triton Inference Server for Linux contains a vulnerability in shared memory APIs, where a user can cause an impro
Denial of service in NVIDIA Triton Inference Server for Linux allows remote unauthenticated attackers to exhaust server
Denial of service in NVIDIA Triton Inference Server for Linux (versions through 26.03) allows a remote attacker to crash
Denial of service in NVIDIA Triton Inference Server for Linux exposes AI inference infrastructure to remote disruption t
Unbounded resource allocation in NVIDIA Triton Inference Server for Linux allows remote, unauthenticated attackers to ex
Same weakness CWE-834 – Excessive Iteration
View allSame technique Denial Of Service
View allShare
External POC / Exploit Code
Leaving vuln.today