Loading story…
NVIDIA disclosed Security Bulletin 5865 for NVIDIA Triton Inference Server, publishing advisory materials and associated MITRE-format CVE records for five vulnerabilities: CVE-2026-47606, CVE-2026-47627, CVE-2026-47628, CVE-2026-47629, and CVE-2026-47630. The bulletin was released through NVIDIA's product-security repository with CSAF, Markdown, checksum, and CVE JSON files, indicating a coordinated vendor advisory covering multiple issues in the inference-serving platform.
The most severe issue publicly detailed is CVE-2026-47627, a critical path traversal vulnerability (CWE-22) affecting NVIDIA Triton Inference Server on Linux in versions 0.0 through 26.05. The CVE record assigns a CVSS v3.1 score of 9.8 with vector AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H, and NVIDIA states that successful exploitation could lead to denial of service.
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
2 events from the most recent confirmed update back to the earliest known activity.
CVE-2026-47627 was published as a critical path traversal vulnerability affecting NVIDIA Triton Inference Server on Linux versions 0.0 through 26.05. NVIDIA states successful exploitation could cause denial of service, and the CVE record assigns a CVSS v3.1 score of 9.8.
NVIDIA published Security Bulletin 5865 for NVIDIA Triton Inference Server in its public product-security repository. The bulletin directory includes advisory files and MITRE-format JSON records for five CVEs, including CVE-2026-47627.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
2 references tracked. Mallory keeps watching after this page renders.
Map indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
NVIDIA patched multiple **critical vulnerabilities** in Triton Inference Server that can let remote, unauthenticated attackers crash or fully compromise AI inference servers exposed over HTTP. The issues affect Triton versions prior to `25.07` on Linux and Windows and include stack and heap memory corruption flaws such as **CVE-2025-23310**, **CVE-2025-23311**, **CVE-2025-23317**, **CVE-2025-23318**, and the related Python-backend chain **CVE-2025-23319**, **CVE-2025-23320**, and **CVE-2025-23334**. Several bugs stem from unsafe HTTP request parsing and chunked transfer handling, while others arise from improper validation in Triton’s shared memory and Python backend components, creating paths to denial of service, information disclosure, data tampering, and remote code execution.
Jun 29, 2026
NVIDIA issued security updates for multiple products across its AI and enterprise software stack, fixing vulnerabilities that could allow **remote code execution**, denial of service, privilege escalation, data tampering, and information disclosure. The most severe issue disclosed in its broader March advisories was `CVE-2025-33244` in **NVIDIA Apex**, a widely used PyTorch extension for mixed-precision and distributed training. High-severity flaws were also addressed in **Triton Inference Server**, **Megatron LM**, **NeMo Framework**, and **Model Optimizer**, with NVIDIA warning that exploitation could disrupt AI workloads, expose sensitive training data, or enable unauthorized access. Medium-severity issues were additionally listed in **VIRTIO-Net**, **SNAP4**, and **B300 MCU**. NVIDIA later released urgent fixes for **TensorRT-LLM** and **Isaac Launchable**, including TensorRT-LLM deserialization flaws in MPI server and RPC testing components that could lead to RCE, data manipulation, information disclosure, or service outages. It also patched a Linux issue in Isaac Launchable involving sensitive information sent in clear text, creating risks of privilege escalation and system disruption. NVIDIA advised customers to upgrade **TensorRT-LLM** to `1.2.1` or later, and said organizations running multi-GPU deployments should use: ```bash trtllm-llmapi-launch ``` to reduce network exposure. The company has also begun publishing PSIRT bulletins on GitHub in Markdown and CSAF formats to support automated vulnerability management and faster remediation.
Jun 29, 2026
NVIDIA disclosed **CVE-2026-24254**, a critical out-of-bounds write vulnerability in **NVIDIA Dynamo for Linux** affecting the **multimodal serving topology**. The flaw impacts versions `0` through `v1.1.0` and carries a **CVSS v3.1 score of 9.8** (`AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`), indicating that it can be exploited remotely without privileges or user interaction. Successful exploitation could lead to **remote code execution**, **privilege escalation**, **data tampering**, **denial of service**, and **information disclosure**. NVIDIA published the issue as part of **Security Bulletin 5842**, which includes bulletin artifacts and references multiple Dynamo-related CVEs; available metadata indicates **no known exploitation** so far, while CISA SSVC data flags the bug as **automatable** with **total technical impact**.
Aug 5, 2026