Lucene search
K

57 matches found

Nuclei
Nuclei
added 12 hours ago2 views

LMDeploy - Server-Side Request Forgery

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 the vision-language module. The loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating internal or...

7.5CVSS6.1AI score0.08696EPSS
Exploits2References3
OSV
OSV
added 2026/05/21 7:33 p.m.4 views

GHSA-9XQ9-36W5-Q796 lmdeploy: Hardcoded trust_remote_code=True is an implicit unsafe remote-code load path with no user opt-out

📋 Reframing 2026-05-02: implicit unsafe remote-code path, not "supply-chain" The accurate description of this vulnerability is: "getmodelarch and related helpers hardcode trustremotecode=True with no opt-out, creating an implicit unsafe remote-code load path on every model fetch." What this repor...

7.8CVSS6.5AI score
Exploits0References2
Github Security Blog
Github Security Blog
added 2026/05/21 7:33 p.m.6 views

lmdeploy: Hardcoded trust_remote_code=True is an implicit unsafe remote-code load path with no user opt-out

📋 Reframing 2026-05-02: implicit unsafe remote-code path, not "supply-chain" The accurate description of this vulnerability is: "getmodelarch and related helpers hardcode trustremotecode=True with no opt-out, creating an implicit unsafe remote-code load path on every model fetch." What this repor...

6.5AI score
Exploits0References2Affected Software1
Github Security Blog
Github Security Blog
added 2026/05/21 5:30 p.m.9 views

LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization

Summary lmdeploy hardcodes trustremotecode=True in multiple HuggingFace model-loading call sites. The affected code paths are in: text lmdeploy/archs.py lmdeploy/utils.py The vulnerable call sites pass trustremotecode=True into HuggingFace Transformers APIs such as AutoConfig.frompretrained,...

6.5AI score
Exploits0References3Affected Software1
OSV
OSV
added 2026/05/21 5:30 p.m.1 views

GHSA-M549-QQ94-FVHG LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization

Summary lmdeploy hardcodes trustremotecode=True in multiple HuggingFace model-loading call sites. The affected code paths are in: text lmdeploy/archs.py lmdeploy/utils.py The vulnerable call sites pass trustremotecode=True into HuggingFace Transformers APIs such as AutoConfig.frompretrained,...

7.8CVSS6.5AI score
Exploits0References3
Positive Technologies
Positive Technologies
added 2026/05/21 12:0 a.m.8 views

PT-2026-42662

Summary lmdeploy hardcodes trust remote code=True in multiple HuggingFace model-loading call sites. The affected code paths are in: text lmdeploy/archs.py lmdeploy/utils.py The vulnerable call sites pass trust remote code=True into HuggingFace Transformers APIs such as AutoConfig.from pretrained,...

7.8CVSS6.7AI score
Exploits0References4
Positive Technologies
Positive Technologies
added 2026/05/21 12:0 a.m.5 views

PT-2026-42614

📋 Reframing 2026-05-02: implicit unsafe remote-code path, not "supply-chain" The accurate description of this vulnerability is: "get model arch and related helpers hardcode trust remote code=True with no opt-out, creating an implicit unsafe remote-code load path on every model fetch." What this...

7.8CVSS6.5AI score
Exploits0References3
Positive Technologies
Positive Technologies
added 2026/05/21 12:0 a.m.5 views

PT-2026-42632

Summary lmdeploy hardcodes trust remote code=True in multiple HuggingFace model-loading call sites. The affected code paths are in: text lmdeploy/archs.py lmdeploy/utils.py The vulnerable call sites pass trust remote code=True into HuggingFace Transformers APIs such as AutoConfig.from pretrained,...

7.8CVSS6.7AI score
Exploits0References4
Positive Technologies
Positive Technologies
added 2026/05/21 12:0 a.m.6 views

PT-2026-42668

📋 Reframing 2026-05-02: implicit unsafe remote-code path, not "supply-chain" The accurate description of this vulnerability is: "get model arch and related helpers hardcode trust remote code=True with no opt-out, creating an implicit unsafe remote-code load path on every model fetch." What this...

7.8CVSS6.5AI score
Exploits0References5
GithubExploit
GithubExploit
added 2026/05/13 5:2 a.m.109 views

Exploit for Server-Side Request Forgery in Internlm Lmdeploy

CVE-2026-33626 — LMDeploy Vision-Language SSRF Lab Overvie...

7.5CVSS5.8AI score0.08696EPSS
Exploits2
The Hacker News
The Hacker News
added 2026/04/24 7:24 a.m.8 views

LMDeploy CVE-2026-33626 Flaw Exploited Within 13 Hours of Disclosure

A high-severity security flaw in LMDeploy, an open-source toolkit for compressing, deploying, and serving large language models LLMs, has come under active exploitation in the wild less than 13 hours after its public disclosure. The vulnerability, tracked as CVE-2026-33626 CVSS score: 7.5, relate...

9.8CVSS8.6AI score0.21968EPSS
Exploits15
RedhatCVE
RedhatCVE
added 2026/04/22 1:22 a.m.1 views

CVE-2026-33626

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 loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating...

7.5CVSS5.9AI score0.08696EPSS
Exploits2References1
VulnCheck KEV
VulnCheck KEV
added 2026/04/22 12:0 a.m.25 views

VulnCheck KEV: CVE-2026-33626

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 loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating...

7.5CVSS5.9AI score0.08696EPSS
In wildExploits2References2
EUVD
EUVD
added 2026/04/21 3:4 p.m.1 views

EUVD-2026-23970

LMDeploy has Server-Side Request Forgery SSRF via Vision-Language Image Loading...

7.5CVSS5.7AI score0.08696EPSS
Exploits2References5
Snyk
Snyk
added 2026/04/21 3:4 p.m.3 views

Server-side Request Forgery (SSRF)

Overview Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the loadimage and encodeimagebase64 functions in LMDeploy's vision-language module, which fetch URLs without validating whether the destination is an internal or private address. An attacker can acce...

8.7CVSS6AI score0.08696EPSS
Exploits2References2
NVD
NVD
added 2026/04/20 9:16 p.m.0 views

CVE-2026-33626

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 loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating...

7.5CVSS0.08696EPSS
Exploits2References4
ATTACKERKB
ATTACKERKB
added 2026/04/20 8:29 p.m.0 views

CVE-2026-33626

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 loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating...

7.5CVSS5.9AI score0.08696EPSS
Exploits2References5Affected Software1
Cvelist
Cvelist
added 2026/04/20 8:29 p.m.26 views

CVE-2026-33626 LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading

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 loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating...

7.5CVSS0.08696EPSS
Exploits2References4
CVE
CVE
added 2026/04/20 8:29 p.m.22 views

CVE-2026-33626

LMDeploy SSRF in the vision-language module (prior to 0.12.3) allows an attacker to fetch arbitrary URLs via load_image() in lmdeploy/vl/utils.py without internal IP validation, potentially reaching cloud metadata services and internal networks. The issue also affects encode_image_base64() and ca...

7.5CVSS5.9AI score0.08696EPSS
In wildExploits2References4Affected Software1
Vulnrichment
Vulnrichment
added 2026/04/20 8:29 p.m.2 views

CVE-2026-33626 LMDeploy Vulnerable to Server-Side Request Forgery (SSRF) via Vision-Language Image Loading

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 loadimage function in lmdeploy/vl/utils.py fetches arbitrary URLs without validating...

7.5CVSS5.9AI score0.08696EPSS
Exploits2References4
Rows per page
Query Builder