Heap-address disclosure via unsanitized PIL exceptions
Published Jun 22, 2026 · Updated Jun 22, 2026
Information disclosure in vLLM before 0.23.1rc0 allows remote attackers to read heap addresses through malformed image requests. Affected Anthropic handlers catch PIL exceptions and return unsanitized str(exc), exposing the BytesIO object representation instead of using sanitize_message. The Anthropic image path is network-reachable without authentication by default; the disclosed address reduces ASLR entropy but does not itself grant code execution.
Summary
What happened
Information disclosure in vLLM before 0.23.1rc0 allows remote attackers to read heap addresses through malformed image requests. Affected Anthropic handlers catch PIL exceptions and return unsanitized str(exc), exposing the BytesIO object representation instead of using sanitize_message. The Anthropic image path is network-reachable without authentication by default; the disclosed address reduces ASLR entropy but does not itself grant code execution.
The record
- CVE
- CVE-2026-54236
- Published
- Jun 22, 2026
- Updated
- Jun 22, 2026
- Vendor
- vLLM Project
- Product
- vLLM
- Classifications
- CWE-532
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 22, 2026CVE publishedPublication date reported by the CVE source.
- Jun 22, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 0.23.1rc0
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA-hgg8-fqqc-vfmw proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo