CVE-2026-54236: vllm · Sensitive Data in Logs
Affects vllmSource CVE Database V5
Mentioned vulnerabilities
Not known to be exploited · public detection template (Nuclei) · CVSS 5.3 Medium : upgrade to 0.23.1rc0 when convenient.
Data as of 5 Nov 2026, 00:01 UTC
- EPSS
- 0.9% chance of exploitation in 30 days – higher than 60% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
- Patch
- Available – fixed in 0.23.1rc0
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:NExploitation evidence
Disclosed: evidence found.
CVE published 22 Jun 2026
Detectable: evidence found.
nuclei template: vLLM <= 0.23.0 - Anthropic Router Heap Address Information Leak
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 5 Nov 2026.
What to do
Upgrade vllm to 0.23.1rc0.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| vllm-projectvllm | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
A fix for this vulnerability is available in vLLM version 0.23.1rc0. Users should upgrade to this version or later to ensure that all exception messages are properly sanitized and memory addresses are not leaked. Until upgraded, avoid exposing the vulnerable API endpoints or WebSocket handlers to untrusted users. Patch status is not explicitly stated beyond the fix in 0.23.1rc0; check the vendor advisory for the latest remediation guidance.
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.