CVE-2026-73555

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validation_exception_handler in vllm/entrypoints/openai/server_utils.py converts FastAPI RequestValidationError objects with str(exc), and sanitize_message in vllm/entrypoints/utils.py does not remove traceback-style file paths, allowing unauthenticated malformed JSON requests to /v1/chat/completions, /v1/completions, /tokenize, and /detokenize to disclose the OS username, home and virtual-environment paths, Python version, internal package structure, line numbers, and endpoint handler names. This issue is fixed in version 0.26.0.

Published 13 Aug 2026, 15:20 UTC Last modified 13 Aug 2026, 15:20 UTC

5.3

CVSS 3.1 MEDIUM base score CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

Attack profile

The conditions required to exploit this vulnerability and its potential impact.

Attack vector Network

Attack complexity Low

Privileges required None

User interaction None

Scope Unchanged

Confidentiality Low

Integrity None

Availability None

Exploitability3.9

Impact1.4

Affected products

Product applicability statements supplied with the NVD record.

NVD has not published structured affected-product data for this record.

Weakness classification

CWE categories help security teams group the underlying software weakness.

CWECWE-209

Source references

External advisories, patches and technical reports attached to this CVE record.

NVD National Vulnerability Database recordnvd.nist.gov 01 Technical reference security-advisories@github.com 02 Technical reference security-advisories@github.com 03 Technical reference security-advisories@github.com 04 Technical reference security-advisories@github.com