CVE-2025-23320
Published: 06 August 2025
Summary
CVE-2025-23320 is a high-severity Generation of Error Message Containing Sensitive Information (CWE-209) vulnerability in Nvidia Triton Inference Server. Its CVSS base score is 7.5 (High).
Operationally, ranked in the top 49.5% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-23836
Vulnerability details
NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause the shared memory limit to be exceeded by sending a very large request. A successful exploit of this vulnerability might…
more
lead to information disclosure.
- CWE(s)
Related Threats
No named actor attribution yet. ATT&CK technique mapping in progress for this CVE.
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Detects error messages that leak sensitive information as evidence of disclosure.
The control directly mitigates generation of error messages containing sensitive authentication details by requiring obscured feedback instead of verbose responses.
Misdirection allows generation of misleading error messages that withhold or falsify sensitive details.
Explicitly requires error messages to avoid including sensitive or exploitable details while still supporting corrective action.
Validation ensures error messages contain only expected, non-sensitive content and blocks leakage via verbose errors.
Fail-safe procedures can be defined to suppress or sanitize error output, reducing generation of messages that contain sensitive information.