BlackTreeCVE Intelligencevllm-project · vllm
Critical technical impact with a remotely reachable, unauthenticated path; no CISA KEV confirmation is currently recorded.
Critical technical impact with a remotely reachable, unauthenticated path; no CISA KEV confirmation is currently recorded.
Patch availablevLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.
vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.
The product writes sensitive information to a log file.
An attacker operating through a network path may attempt exploitation without authentication or user interaction. If successful, the issue may execute code or commands in the affected security context.
vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.
The product writes sensitive information to a log file.
An attacker operating through a network path may attempt exploitation without authentication or user interaction. If successful, the issue may execute code or commands in the affected security context.
CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.
No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.
No exploit-tagged reference or CISA SSVC proof-of-concept state is currently recorded. Research may still exist outside the structured feeds.
CWE-532: Insertion of Sensitive Information into Log File. The product writes sensitive information to a log file.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:HCommon Vulnerability Scoring System 3.1: the compact vector below is decoded into plain language.
Operational remediation based on structured source evidence.
Published 2 Feb 2026 · Last source change 15 Jul 2026, 01:19 UTC · CWE-532 · Insertion of Sensitive Information into Log File
Core structured fields are present and their contributing authorities are shown above.
No material field changes have been recorded since change tracking began. Routine source refreshes and cosmetic edits are intentionally excluded.