Internal resource disclosure via unvalidated image URLs
Published Apr 20, 2026 · Updated Apr 20, 2026
SSRF in InternLM LMDeploy before 0.12.3 allows remote attackers to read internal resources through a crafted vision-model image URL. An image URL supplied to /v1/chat/completions reaches the vision-language loader, which performs an HTTP request without rejecting private, loopback, link-local, or metadata-service addresses. An exposed vision-language API with default authentication settings is sufficient to disclose cloud credentials or probe internal services reachable from the server.
Summary
What happened
SSRF in InternLM LMDeploy before 0.12.3 allows remote attackers to read internal resources through a crafted vision-model image URL. An image URL supplied to /v1/chat/completions reaches the vision-language loader, which performs an HTTP request without rejecting private, loopback, link-local, or metadata-service addresses. An exposed vision-language API with default authentication settings is sufficient to disclose cloud credentials or probe internal services reachable from the server.
The record
- CVE
- CVE-2026-33626
- Published
- Apr 20, 2026
- Updated
- Apr 20, 2026
- Vendor
- InternLM
- Product
- LMDeploy
- Classifications
- CWE-918, CAPEC-664, T1046, T1552.005
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Apr 20, 2026CVE publishedPublication date reported by the CVE source.
- Apr 20, 2026Record updatedLatest update available in the CVE record.
- Apr 22, 2026Exploitation reportedSysdig LMDeploy honeypot exploitation
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=< 0.12.3
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-6w67-hwm5-92mq verified SSRF proof of conceptproof of concept · validated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Reported exploitation
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