CVE-2026-54236
vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
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.
INFO
Published Date :
June 22, 2026, 11:16 p.m.
Last Modified :
June 24, 2026, 4:53 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | MEDIUM | [email protected] |
Solution
- Update vLLM to version 0.23.1rc0 or later.
- Ensure all response paths sanitize exception messages.
- Review error handling for sensitive data exposure.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-54236.
| URL | Resource |
|---|---|
| https://github.com/vllm-project/vllm/commit/94923629729381d7f7c9efde72071a2441f7fd82 | Patch |
| https://github.com/vllm-project/vllm/pull/45119 | Issue Tracking |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw | Exploit Third Party Advisory |
| https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw | Exploit Third Party Advisory |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-54236 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-54236
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-54236 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-54236 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
Initial Analysis by [email protected]
Jun. 24, 2026
Action Type Old Value New Value Added CPE Configuration OR *cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* versions up to (excluding) 0.23.1 Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/commit/94923629729381d7f7c9efde72071a2441f7fd82 Types: Patch Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/pull/45119 Types: Issue Tracking Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw Types: Exploit, Third Party Advisory Added Reference Type CISA-ADP: https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw Types: Exploit, Third Party Advisory -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 23, 2026
Action Type Old Value New Value Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw Added SSVC {'id': 'CVE-2026-54236', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'yes'}, {'technicalImpact': 'partial'}], 'version': '2.0.3', 'timestamp': '2026-06-23T12:32:56.752434Z'} -
New CVE Received by [email protected]
Jun. 22, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'vllm-project', 'product': 'vllm', 'versions': [{'status': 'affected', 'version': '< 0.23.1rc0'}]}] Added 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. Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N Added CWE CWE-532 Added Reference https://github.com/vllm-project/vllm/commit/94923629729381d7f7c9efde72071a2441f7fd82 Added Reference https://github.com/vllm-project/vllm/pull/45119 Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw