Lucene search
+L

82 matches found

CVE
CVE
added 2026/06/09 11:5 p.m.53 views

CVE-2026-46517

LMDeploy has a hardcoded trust_remote_code=True path in multiple code locations (e.g., get_model_arch and related calls) that is invoked for every model load. This creates an implicit unsafe remote-code load path when loading HuggingFace models from a repository, with no user opt-out or CLI flag ...

7.8CVSS5.4AI score0.00148EPSS
SaveExploits0References1
Vulnrichment
Vulnrichment
added 2026/06/09 11:5 p.m.8 views

CVE-2026-46432 LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization

LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded "trustremotecode=True" in multiple HuggingFace model-loading call sites. At time of publication, there are no...

7.8CVSS6.2AI score0.00142EPSS
SaveExploits0References1
OSV
OSV
added 2026/06/09 11:5 p.m.8 views

CVE-2026-46432 LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization

LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded "trustremotecode=True" in multiple HuggingFace model-loading call sites. At time of publication, there are no...

7.8CVSS6.6AI score
SaveExploits0References3
CVE
CVE
added 2026/06/09 11:5 p.m.67 views

CVE-2026-46432

CVE-2026-46432 (LMDeploy) affects lmdeploy

7.8CVSS6.2AI score0.00142EPSS
SaveExploits0References1
EUVD
EUVD
added 2026/06/09 11:5 p.m.16 views

EUVD-2026-35873

LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded "trustremotecode=True" in multiple HuggingFace model-loading call sites. At time of publication, there are no...

7.8CVSS6.2AI score0.00142EPSS
SaveExploits0References1
Cvelist
Cvelist
added 2026/06/09 11:5 p.m.46 views

CVE-2026-46432 LMDeploy: Arbitrary code execution via hardcoded trust_remote_code=True in lmdeploy model initialization

LMDeploy is a toolkit for compressing, deploying, and serving large language models. In versions 0.12.3 and prior, LMDeploy is vulnerable to arbitrary code execution through hardcoded "trustremotecode=True" in multiple HuggingFace model-loading call sites. At time of publication, there are no...

7.8CVSS0.00142EPSS
SaveExploits0References1
OSV
OSV
added 2026/05/21 7:33 p.m.19 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 score0.00148EPSS
SaveExploits0References3
Github Security Blog
Github Security Blog
added 2026/05/21 7:33 p.m.15 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...

7.8CVSS6.5AI score0.00148EPSS
SaveExploits0References3Affected Software1
OSV
OSV
added 2026/05/21 5:30 p.m.15 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 score0.00142EPSS
SaveExploits0References4
Github Security Blog
Github Security Blog
added 2026/05/21 5:30 p.m.20 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,...

7.8CVSS6.5AI score0.00142EPSS
SaveExploits0References4Affected Software1
Positive Technologies
Positive Technologies
added 2026/05/21 12:0 a.m.25 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
SaveExploits0References4
Positive Technologies
Positive Technologies
added 2026/05/21 12:0 a.m.21 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
SaveExploits0References3
Positive Technologies
Positive Technologies
added 2026/05/21 12:0 a.m.22 views

PT-2026-42668

Name of the Vulnerable Software and Affected Versions LMDeploy versions 0.12.3 and earlier Description LMDeploy contains an implicit unsafe remote-code load path because it hardcodes the trust remote code=True parameter when fetching models. This configuration overrides the default-secure stance ...

7.8CVSS6.5AI score0.00148EPSS
SaveExploits0References13
Positive Technologies
Positive Technologies
added 2026/05/21 12:0 a.m.26 views

PT-2026-42662

Name of the Vulnerable Software and Affected Versions LMDeploy versions 0.12.3 and earlier Description LMDeploy is a toolkit for compressing, deploying, and serving large language models. The software hardcodes trust remote code=True in multiple HuggingFace model-loading call sites, specifically...

7.8CVSS6.2AI score0.00142EPSS
SaveExploits0References12
GithubExploit
GithubExploit
added 2026/05/13 5:2 a.m.291 views

Exploit for Server-Side Request Forgery in Internlm Lmdeploy

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

7.5CVSS5.8AI score0.4525EPSS
SaveExploits2
The Hacker News
The Hacker News
added 2026/04/24 7:24 a.m.18 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 score0.57807EPSS
SaveExploits19
RedhatCVE
RedhatCVE
added 2026/04/22 1:22 a.m.8 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 score0.4525EPSS
SaveExploits2References1
VulnCheck KEV
VulnCheck KEV
added 2026/04/22 12:0 a.m.44 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 score0.4525EPSS
SaveIn wildExploits2References2
Snyk
Snyk
added 2026/04/21 3:4 p.m.6 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 score0.4525EPSS
SaveExploits2References2
EUVD
EUVD
added 2026/04/21 3:4 p.m.39 views

EUVD-2026-23970

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

7.5CVSS5.7AI score0.4525EPSS
SaveExploits2References5
Rows per page
Query Builder