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.
Scoring
- Severity
- MEDIUM
- CVSS base score
- 5.3
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
- EPSS probability
- 0.26%
- CWE
- CWE-209
- Published
- 2026-08-13
- Last modified
- 2026-08-14
Affected products
- vllm-project vllm
Weakness type
Related vulnerabilities
- CVE-2026-66306 — Skype for Business Information Disclosure Vulnerability
- CVE-2026-69294 — Microsoft COM for Windows Information Disclosure Vulnerability
- CVE-2026-68886 — Windows Network Connection Broker Information Disclosure Vulnerability
- CVE-2026-67383 — Microsoft SQL Server Information Disclosure Vulnerability
- CVE-2026-69684 — Windows Error Reporting Information Disclosure Vulnerability
- CVE-2026-69552 — Windows Print Spooler Components Information Disclosure Vulnerability
- CVE-2026-11873 — Pki-core: dogtag-pki: empty request to dogtag /ca/rest/certrequests causes http 500, java exception, and stacktrace disclosure
- CVE-2026-82739 — Ash.Resource.Validation.Confirm leaks a confirmed field's stored value in the atomic mismatch error