CVE-2026-54236

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-532

• https://github.com/vllm-project/vllm/commit/94923629729381d7f7c9efde72071a2441f7fd82Patch
• https://github.com/vllm-project/vllm/pull/45119Issue Tracking
• https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmwExploit, Third Party Advisory
• https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmwExploit, Third Party Advisory

Published

Jun 22, 2026

Last Modified

Jun 24, 2026

Status

Analyzed

• How Strix found a critical auth bypass in etcdStrix autonomously discovered a critical authentication bypass in etcd, later designated CVE-2026-33413.
• Autonomous PentestingAI agents that find and validate exploitable vulnerabilities like this one across your applications.
• PR ReviewsPentest every pull request so vulnerable code is caught before it ships to production.
• AI Penetration TestingHow AI-driven penetration testing continuously covers your attack surface.

• CVE-2026-54230A symlink following vulnerability was found in the ABRT post…7.8
• CVE-2026-54231A content injection vulnerability was found in the ABRT post…5.5
• CVE-2026-54232vLLM is an inference and serving engine for large language m…8.8
• CVE-2026-54233vLLM is an inference and serving engine for large language m…6.5
• CVE-2026-54234vLLM is a high-throughput and memory-efficient inference and…7.5
• CVE-2026-54235vLLM is an inference and serving engine for large language m…6.5
• CVE-2026-54242Statamic is a Laravel and Git powered content management sys…4.9
• CVE-2026-54243Statamic is a Laravel and Git powered content management sys…6.1
• CVE-2026-54244Statamic is a Laravel and Git powered content management sys…3.5
• CVE-2026-54249Pydantic AI is a Python agent framework for building Generat…6.8
• CVE-2026-5425The Widgets for Social Photo Feed plugin for WordPress is vu…7.2
• CVE-2026-54250K3s is a fully conformant production-ready Kubernetes distri…5.8