InternLM lmdeploy up to 0.12.2 lmdeploy/vl/utils.py load_image server-side request forgery

CVSS Meta Temp Score
CVSS is a standardized scoring system to determine possibilities of attacks. The Temp Score considers temporal factors like disclosure, exploit and countermeasures. The unique Meta Score calculates the average score of different sources to provide a normalized scoring system.
Current Exploit Price (≈)
Our analysts are monitoring exploit markets and are in contact with vulnerability brokers. The range indicates the observed or calculated exploit price to be seen on exploit markets. A good indicator to understand the monetary effort required for and the popularity of an attack.
CTI Interest Score
Our Cyber Threat Intelligence team is monitoring different web sites, mailing lists, exploit markets and social media networks. The CTI Interest Score identifies the interest of attackers and the security community for this specific vulnerability in real-time. A high score indicates an elevated risk to be targeted for this vulnerability.
7.2$0-$5k0.00

Summaryinfo

A vulnerability marked as critical has been reported in InternLM lmdeploy up to 0.12.2. Affected by this vulnerability is the function load_image of the file lmdeploy/vl/utils.py. This manipulation causes server-side request forgery. The identification of this vulnerability is CVE-2026-33626. It is possible to initiate the attack remotely. There is no exploit available. It is suggested to upgrade the affected component.

Detailsinfo

A vulnerability was found in InternLM lmdeploy up to 0.12.2. It has been declared as critical. Affected by this vulnerability is the function load_image of the file lmdeploy/vl/utils.py. The manipulation with an unknown input leads to a server-side request forgery vulnerability. The CWE definition for the vulnerability is CWE-918. The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination. As an impact it is known to affect confidentiality, integrity, and availability. The summary by CVE is:

LMDeploy is a toolkit for compressing, deploying, and serving large language models. Versions prior to 0.12.3 have a Server-Side Request Forgery (SSRF) vulnerability in LMDeploy's vision-language module. The `load_image()` function in `lmdeploy/vl/utils.py` fetches arbitrary URLs without validating internal/private IP addresses, allowing attackers to access cloud metadata services, internal networks, and sensitive resources. Version 0.12.3 patches the issue.

The advisory is shared at github.com. This vulnerability is known as CVE-2026-33626 since 03/23/2026. The exploitation appears to be easy. The attack can be launched remotely. The exploitation doesn't need any form of authentication. Technical details are known, but no exploit is available.

Upgrading to version 0.12.3 eliminates this vulnerability. The upgrade is hosted for download at github.com. Applying the patch 71d64a339edb901e9005358e0633fbbab367d626 is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.

The vulnerability is also documented in the vulnerability database at CERT Bund (WID-SEC-2026-1228). Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Affected

  • Debian Linux
  • Red Hat Enterprise Linux
  • SUSE Linux
  • Oracle Linux
  • SUSE openSUSE
  • RESF Rocky Linux
  • Mozilla Thunderbird
  • Mozilla Firefox ESR
  • Mozilla Firefox

Productinfo

Vendor

Name

Version

License

Website

CPE 2.3info

CPE 2.2info

CVSSv4info

VulDB Vector: 🔒
VulDB Reliability: 🔍

CVSSv3info

VulDB Meta Base Score: 7.4
VulDB Meta Temp Score: 7.2

VulDB Base Score: 7.3
VulDB Temp Score: 7.0
VulDB Vector: 🔒
VulDB Reliability: 🔍

CNA Base Score: 7.5
CNA Vector (GitHub_M): 🔒

CVSSv2info

AVACAuCIA
💳💳💳💳💳💳
💳💳💳💳💳💳
💳💳💳💳💳💳
VectorComplexityAuthenticationConfidentialityIntegrityAvailability
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock

VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍

Exploitinginfo

Class: Server-side request forgery
CWE: CWE-918
CAPEC: 🔒
ATT&CK: 🔒

Physical: No
Local: No
Remote: Yes

Availability: 🔒
Status: Not defined

EPSS Score: 🔒
EPSS Percentile: 🔒

Price Prediction: 🔍
Current Price Estimation: 🔒

0-DayUnlockUnlockUnlockUnlock
TodayUnlockUnlockUnlockUnlock

Threat Intelligenceinfo

Interest: 🔍
Active Actors: 🔍
Active APT Groups: 🔍

Countermeasuresinfo

Recommended: Upgrade
Status: 🔍

0-Day Time: 🔒

Upgrade: lmdeploy 0.12.3
Patch: 71d64a339edb901e9005358e0633fbbab367d626

Timelineinfo

03/23/2026 CVE reserved
04/21/2026 +28 days Advisory disclosed
04/21/2026 +0 days VulDB entry created
05/15/2026 +24 days VulDB entry last update

Sourcesinfo

Product: github.com

Advisory: GHSA-6w67-hwm5-92mq
Status: Confirmed

CVE: CVE-2026-33626 (🔒)
GCVE (CVE): GCVE-0-2026-33626
GCVE (VulDB): GCVE-100-358369
CERT Bund: WID-SEC-2026-1228 - Mozilla Thunderbird, Firefox ESR und Firefox: Mehrere Schwachstellen

Entryinfo

Created: 04/21/2026 06:46
Updated: 05/15/2026 11:19
Changes: 04/21/2026 06:46 (69), 05/15/2026 11:19 (7)
Complete: 🔍
Cache ID: 216::103

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Discussion

No comments yet. Languages: en.

Please log in to comment.

◂ PreviousOverviewNext ▸

Want to stay up to date on a daily basis?

Enable the mail alert feature now!