Authorization Bypass Through User-Controlled Key Affecting vllm package, versions [,0.30.0)
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applicationsSnyk Learn
Learn about Authorization Bypass Through User-Controlled Key vulnerabilities in an interactive lesson.
Start learning- Snyk IDSNYK-PYTHON-VLLM-20877482
- published13 Oct 2026
- disclosed5 Oct 2026
- creditUnknown
Introduced: 5 Oct 2026
NewCVE-2026-105755 (opens in a new tab)How to fix?
Upgrade vllm to version 0.30.0 or higher.
Overview
vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs
Affected versions of this package are vulnerable to Authorization Bypass Through User-Controlled Key in _flash_late_interaction_encode_queries and _flash_late_interaction_encode_docs in vllm/entrypoints/pooling/scoring/serving.py, late-interaction query cache keys are derived deterministically from the caller-supplied request_id. An authenticated attacker can predict the cache key for another user's query by knowing or guessing the request_id, then supply document inputs that reference those keys to read cached query embeddings or corrupt scoring results, achieving limited information disclosure and integrity impact.