CVE-2026-54236: vllm-project vllm

Vulnerability summary

CVE-2026-54236 is a medium (CVSS 5.3) vulnerability in vllm-project vllm. EPSS estimates a 0.93% chance of exploitation in the next 30 days, higher than 60% of scored vulnerabilities. 1 public exploit is recorded.

Timeline

1. 22-06-2026
   PublishedVulnerability first disclosed.
2. 23-06-2026
   Last modifiedVulnerability information updated.

Description

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.

• CWE-532Insertion of Sensitive Information into Log FileThe product writes sensitive information to a log file.