20588 matches found
Smarter Saboteurs, Better Fixers: Scaling and Security in Linear Multi-Agent Workflows
As LLM-based multi-agent systems MAS are deployed in the wild, the resilience of their collaboration structures against adversarial compromise becomes a critical safety concern. Attackers may leverage prompt-injection or jailbreaking to sabotage individual agents within MAS workflows, but the...
lmdeploy: Code injection vulnerability
lmdeploy is a toolkit developed by InternLM for compressing, deploying, and serving LLMs. Versions of lmdeploy prior to 0.12.3 have a code injection vulnerability. This vulnerability stems from the hardcoding of trustremotecode=True at multiple HuggingFace model loading points, which may allow...
Mind Your Key: An Empirical Study of LLM API Credential Leakage in IOS Apps
The rapid integration of large language models LLMs into mobile applications has introduced a new class of credential security risk: leaked credentials that grant unauthorized access to LLM inference services, causing financial damage to developers. Prior work on credential leakage has focused...
PT-2026-48537
Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.22.0 Description vLLM is an inference and serving engine for large language models. The software contains a supply-chain integrity issue where revision pinning controls are not consistently applied to all artifacts...
CVE-2026-46432: Improper Control of Generation of Code
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...
SQLAlchemy Admin security vulnerabilities
SQLAlchemy Admin is an open-source SQLAlchemy model management interface tool developed by Smithy HQ. Versions of SQLAlchemy Admin prior to 0.25.1 contained a security vulnerability. This vulnerability stemmed from the ajaxlookup endpoint in the application.py file, which bypassed the isaccessibl...
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...
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...
CVE-2026-46432
CVE-2026-46432 (LMDeploy) affects lmdeploy
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...
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...
MAL-2026-5479 Malicious code in mcp-server-github (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 156761c4bd0e22759f082d7c030c241be12301dced1e58943c17aaacf9fe0958 Package squats the unscoped name mcp-server-github to intercept installs intended for the official @modelcontextprotocol/server-github. package.json...
Malicious code in db-xorma (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 1428486c71a3cd7d89ea90a17631bb5dc0fee7e11a6cbb4d8029a8b25268c7d2 db-xorma advertises itself as a reactive in-memory database library. When a consumer creates any Model instance the documented entry point, the...
MINI-P44H-M6MG-8V55
Bulletin has no description...
MINI-M438-X262-HFFJ
Bulletin has no description...
MINI-G4VR-4P8P-6FHM
Bulletin has no description...
MINI-MM48-3PHJ-RPGH
Bulletin has no description...
MINI-PG77-MC2F-96MM
Bulletin has no description...