CVE-2026-73555: vLLM: Unauthenticated Internal Path and Username Disclosure via Validation Error Messages
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validationexceptionhandler in vllm/entrypoints/openai/serverutils.py converts FastAPI RequestValidationError objects with str(exc), and sanitizemessage 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.
Affected Software
Remediation
Recommended actions to resolve this vulnerability, in priority order.
- Upgrade
Upgrade
vllmto a version that resolves this vulnerability.Fixed in 0.26.0
Event History
Frequently Asked Questions
What is the severity of CVE-2026-73555?
The severity of CVE-2026-73555 is medium with a score of 5.3.
What does CVE-2026-73555 affect?
CVE-2026-73555 affects vLLM, which is an inference and serving engine for large language models.
How does CVE-2026-73555 impact system security?
CVE-2026-73555 allows unauthenticated internal path and username disclosure via validation error messages.
How do I fix CVE-2026-73555?
To fix CVE-2026-73555, upgrade vLLM to version 0.26.0 or later, which addresses the issue.
What is the nature of the vulnerability in CVE-2026-73555?
CVE-2026-73555 is caused by ineffective handling of FastAPI RequestValidationError objects that leads to sensitive information exposure.