CVE-2026-54236
MediumCVSS 5.3Exploitation Probability (EPSS)
Elevated risk53th percentile — higher than 53% of all known CVEs
Summary
vLLM is an inference and serving engine for large language models. In versions prior to 0.23.1rc0, an incomplete fix for CVE-2026-22778 allows memory addresses to leak in error messages, potentially exposing memory information in responses to clients.
Risk Assessment
The organization may be vulnerable to attacks where unauthorized users can access sensitive memory information, leading to further exploits or attacks on the system.
Recommendation
It is recommended to upgrade to version 0.23.1rc0 or later to patch this vulnerability and secure the system against potential attacks.
Original NVD description (English source)
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo str(exc) directly to clients without calling sanitize_message. The unsanitized sites include the Anthropic API router in vllm/entrypoints/anthropic/api_router.py (the POST /v1/messages and POST /v1/messages/count_tokens handlers), the Server-Sent Events streaming converter in vllm/entrypoints/anthropic/serving.py, and the realtime speech-to-text WebSocket in vllm/entrypoints/speech_to_text/realtime/connection.py. These paths catch the exception inside the route coroutine and construct the JSONResponse themselves, bypassing the sanitizing global FastAPI exception handler, and WebSocket frames do not traverse that handler chain at all. Using the same primitive as the parent issue, an unauthenticated attacker can send malformed image bytes through the Anthropic Messages API image content parts so that PIL.Image.open raises an UnidentifiedImageError whose message contains the BytesIO object repr, leaking the heap memory address verbatim in the error.message field of the response body. This vulnerability is fixed in 0.23.1rc0.