medium6.9
CVE-2026-126395
vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitize_message() whose lowercase-only regex fails to scrub uppercase PI…
Impact
vLLM from 0.14.0rc1 before 0.31.0 contains an information disclosure vulnerability in sanitize_message() whose lowercase-only regex fails to scrub uppercase PIL image addresses. Unauthenticated attackers can send a crafted PNG to endpoints such as /tokenize, triggering HF-processor errors that leak live server heap addresses useful for ASLR bypass.
An attacker can exploit this over the network, without logging in, without any action by a user. If it succeeds: low risk of data being read.
Affected products · Vllm-project
| Product | Affected versions |
|---|---|
| Vllm | from 0.14.0rc1 before 0.31.0 |
Weakness classification
References
- NVD record
- CVE.org record
- GitHub advisory
- https://github.com/vllm-project/vllm/security/advisories/GHSA-m9fg-w9qh-67pc
- https://www.vulncheck.com/advisories/vllm-0.14-0rc1-before-0.31.0-heap-address-disclosure-via-sanitize-message
- https://github.com/advisories/GHSA-8hqr-48h6-r93j
- https://nvd.nist.gov/vuln/detail/CVE-2026-126395