CVE-2026-54236
What it is
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.
At a glance
- Exploitability
- Can be exploited over the network without logging in. Limited direct impact.
- Exploit odds
- 0.9% chance of exploitation in the next 30 days (EPSS).
- Fix
- A patch, advisory or fixed version is referenced. Upgrade or apply it.
Timeline
- PublishedDisclosed publicly on CVE.org and NVD
- Last updatedMost recent change to the record
Why it ranks here
- Exploited in the wild: no, CISA does not list it.
- Exploit odds: 0.9% in the next 30 days (EPSS).
- Severity: 5.3 MEDIUM (CVSS).
- Fix: a patch or advisory is linked.
Details
- Published
- Last modified
- Exploit probability
- 0.9% · EPSS, next 30 days
- Weakness
- CWE-532 · Secrets in logs
- Record status
- Analyzed
Affected
- Vllm < 0.23.1
Attack profile CVSS 3.1 · 5.3
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- Low
- Integrity
- None
- Availability
- None
Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Is it in your code?
Hand this to your coding agent. It searches your project for the affected products and checks versions. Nothing leaves your machine.
Read https://cve-list.com/agent/cve/CVE-2026-54236.md and follow it. Check whether this project is affected by CVE-2026-54236. Read only. Don't change anything and don't upload my code. Tell me yes, no or not sure, with the file as proof.
Fix and advisories
- https://github.com/vllm-project/vllm/commit/94923629729381d7f7c9efde72071a2441f7fd82
- https://github.com/vllm-project/vllm/pull/45119
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw
- https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw