Skip to main content

CVE-2025-23316 / CVE-2025-23268 / CVE-2025-23331: Command Injection and DoS in the September 2025 Triton Bulletin

CVEScoreTypePatchedDisclosed
CVE-2025-233169.8 CriticalOS command injection — Python backendv25.08September 16, 2025
CVE-2025-232688.0 HighImproper input validation — DALI backendv25.08September 16, 2025
CVE-2025-23331MediumDoS via unbounded memory allocationv25.08September 16, 2025

CVE-2025-23268 reported via Trend Micro Zero Day Initiative.

For executives

Six weeks after patching seven critical vulnerabilities in Triton Inference Server, NVIDIA published a further bulletin. CVE-2025-23316 is a command injection flaw in Triton's model control API. An attacker who sends a crafted model name to that API can execute arbitrary OS commands on the server — no authentication, no existing access, nothing but a network connection and a malformed string. CVSS 9.8.

The flaw: CVE-2025-23316

The Python backend does not sanitise the model name parameter before incorporating it into system-level operations. An attacker can include shell metacharacters or command sequences in the model name — characters like ;, |, $(), or backticks — that the underlying OS interprets as separate commands to execute. This is OS command injection (CWE-78).

CVE-2025-23268: DALI backend input validation

NVIDIA's DALI (Data Augmentation Library for Inference) backend handles data preprocessing pipelines within Triton. CVE-2025-23268 is an improper input validation vulnerability where an attacker can cause code execution via a crafted request. CVSS 8.0.

CVE-2025-23331: denial of service via unbounded memory allocation

The HTTP and gRPC endpoints extract size parameters from the request body and use those parameters to allocate memory. CVE-2025-23331 is missing bounds checking on those size values. An attacker sends a single crafted request with an excessively large size field, crashing the server.

Patch and mitigation

Upgrade NVIDIA Triton Inference Server and its Python backend to version 25.08 or later.