CVE-2026-33626: CWE-918: Server-Side Request Forgery (SSRF) in InternLM lmdeploy
LMDeploy versions prior to 0. 12. 3 contain a Server-Side Request Forgery (SSRF) vulnerability in the vision-language module. The vulnerability arises because the load_image() function fetches arbitrary URLs without validating whether the addresses are internal or private. This flaw allows attackers to potentially access internal network resources, including cloud metadata services. The issue is fixed in version 0. 12. 3.
AI Analysis
Technical Summary
CVE-2026-33626 is a high-severity SSRF vulnerability (CWE-918) in InternLM's lmdeploy toolkit, specifically in versions before 0.12.3. The vulnerability exists in the load_image() function within lmdeploy/vl/utils.py, which does not validate URLs for internal or private IP addresses before fetching them. This lack of validation enables attackers to make the server perform unauthorized requests to internal resources, such as cloud metadata services or other sensitive internal network endpoints. The vulnerability has a CVSS 3.1 base score of 7.5, indicating a high impact on confidentiality with no required privileges or user interaction. The vulnerability was publicly disclosed on 2026-04-20, and the vendor has released version 0.12.3 to address the issue.
Potential Impact
Successful exploitation of this SSRF vulnerability can lead to unauthorized access to sensitive internal resources, including cloud metadata services, which may expose confidential information. The vulnerability impacts confidentiality but does not affect integrity or availability. There are no known exploits in the wild at this time.
Mitigation Recommendations
Upgrade lmdeploy to version 0.12.3 or later, where this SSRF vulnerability is patched. Since the vendor advisory does not specify any other mitigation or temporary fixes, applying the official update is the recommended remediation. Patch status is not explicitly confirmed in the advisory fields but the description states version 0.12.3 fixes the issue.
CVE-2026-33626: CWE-918: Server-Side Request Forgery (SSRF) in InternLM lmdeploy
Description
LMDeploy versions prior to 0. 12. 3 contain a Server-Side Request Forgery (SSRF) vulnerability in the vision-language module. The vulnerability arises because the load_image() function fetches arbitrary URLs without validating whether the addresses are internal or private. This flaw allows attackers to potentially access internal network resources, including cloud metadata services. The issue is fixed in version 0. 12. 3.
CVSS v3.1
Score 7.5high
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-33626 is a high-severity SSRF vulnerability (CWE-918) in InternLM's lmdeploy toolkit, specifically in versions before 0.12.3. The vulnerability exists in the load_image() function within lmdeploy/vl/utils.py, which does not validate URLs for internal or private IP addresses before fetching them. This lack of validation enables attackers to make the server perform unauthorized requests to internal resources, such as cloud metadata services or other sensitive internal network endpoints. The vulnerability has a CVSS 3.1 base score of 7.5, indicating a high impact on confidentiality with no required privileges or user interaction. The vulnerability was publicly disclosed on 2026-04-20, and the vendor has released version 0.12.3 to address the issue.
Potential Impact
Successful exploitation of this SSRF vulnerability can lead to unauthorized access to sensitive internal resources, including cloud metadata services, which may expose confidential information. The vulnerability impacts confidentiality but does not affect integrity or availability. There are no known exploits in the wild at this time.
Mitigation Recommendations
Upgrade lmdeploy to version 0.12.3 or later, where this SSRF vulnerability is patched. Since the vendor advisory does not specify any other mitigation or temporary fixes, applying the official update is the recommended remediation. Patch status is not explicitly confirmed in the advisory fields but the description states version 0.12.3 fixes the issue.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-03-23T14:24:11.617Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 69e6941f19fe3cd2cd32c48f
Added to database: 4/20/2026, 9:01:19 PM
Last enriched: 4/28/2026, 6:02:42 AM
Last updated: 6/5/2026, 12:46:37 AM
Views: 135
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.