CVE-2026-54236 Details
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.
A vulnerability in vLLM, an inference engine for large language models, allows for the leakage of memory addresses through several response paths in the Anthropic API and real-time speech-to-text WebSocket. This issue arises because the error messages are not properly sanitized before being sent to the client, leaving sensitive information exposed. The vulnerability affects vLLM versions prior to 0.23.1rc0.
Users can update to vLLM version 0.23.1rc0 or later, where this vulnerability has been fixed.
Metrics
CVSS 4.0 Severity and Vector Strings:
No CVSS 4.0 data is available for this CVE.
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
CISA-ADP
Assessed Jun 23, 2026References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw | CISA-ADP | ExploitThird Party Advisory |
| https://github.com/vllm-project/vllm/commit/94923629729381d7f7c9efde72071a2441f7fd82 | [email protected] | Patch |
| https://github.com/vllm-project/vllm/pull/45119 | [email protected] | Issue Tracking |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw | [email protected] | ExploitThird Party Advisory |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-532 | Insertion of Sensitive Information into Log File | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| vllm vllm | < 0.23.1 |
CPE
Remediation
| |
Change History
4 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Oct 25, 2026 | CVE Translated | [email protected] |
| Jun 24, 2026 | Initial Analysis | [email protected] |
| Jun 23, 2026 | CVE Modified | CISA-ADP |
| Jun 22, 2026 | New CVE Received | [email protected] |