CVE-2026-47629: 
Triton Inference Server vulnerability analysis and mitigation

CVE-2026-47629 is an improper input validation vulnerability in NVIDIA Triton Inference Server for Linux that allows an unauthenticated network attacker to cause a denial of service. It affects all versions of Triton Inference Server up to and including version 26.05. The vulnerability was published on August 18, 2026, and a patch was made available by September 1, 2026. It carries a CVSS v3.1 base score of 7.5 (High) (Feedly, NVIDIA Product Security).

The vulnerability is classified as CWE-20 (Improper Input Validation), meaning the server fails to adequately validate or sanitize attacker-supplied input before processing it. An unauthenticated remote attacker can send malformed or specially crafted input over the network to the Triton Inference Server, triggering a crash or making the service unavailable. No authentication, user interaction, or elevated privileges are required for exploitation, and the attack complexity is low, making it straightforward to automate (Feedly, NVIDIA Product Security).

Successful exploitation results in a denial of service, causing the Triton Inference Server to crash or become unavailable. The impact is limited to availability — there is no assessed impact on confidentiality or integrity of data. Organizations relying on Triton Inference Server for AI/ML inference workloads could experience service disruption, potentially affecting downstream applications and pipelines that depend on the server (Feedly).

There is no public proof-of-concept exploit and no evidence of in-the-wild exploitation as of the time of publication (Feedly). The vulnerability is rated automatable by NVD's SSVC assessment, meaning exploitation can be scripted without manual interaction. The EPSS score is approximately 0.346%, indicating a low probability of exploitation in the near term. No threat actor attribution has been reported, and the vulnerability is not listed in the CISA Known Exploited Vulnerabilities (KEV) catalog (Feedly).

NVIDIA has released a patch addressing this vulnerability; users should update NVIDIA Triton Inference Server to a version newer than 26.05 (NVIDIA Product Security). As interim mitigations, organizations should restrict network access to the Triton Inference Server to trusted clients only, implement network-level input validation and rate limiting, and monitor for abnormal input patterns or unexpected service availability issues (Feedly).

The vulnerability received routine coverage from security aggregators and vulnerability tracking services shortly after disclosure, including mentions on Mastodon, Bluesky, and security news outlets such as SecurityOnline.info (Feedly). No significant researcher commentary or vendor statements beyond the official NVIDIA security bulletin have been identified. Community reaction has been low-key, consistent with the moderate severity and lack of active exploitation.