643 matches found
MAL-2025-191929 Malicious code in wei516-enconly (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 3e40931688b41ac8340ab8f27604ba32f1ea6e364df1e614343cbc4cf0df50e8 Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...
MAL-2025-191926 Malicious code in wayspiritmcp-tpa (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 523cbbda7a0fda2addfcd432b1bfcc1df072ee67a593ffce535b7da7005caae8 Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...
MAL-2025-191925 Malicious code in wayspiritmcp-ppa (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 efa23f0b46a88dcde4aa71c67cba31f46d0f8a9eef555daa0cbe4f2bd54d7a38 Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...
Malicious code in wayspiritmcp-ppa (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 efa23f0b46a88dcde4aa71c67cba31f46d0f8a9eef555daa0cbe4f2bd54d7a38 Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...
Malicious code in wayspiritmcp-enconly (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 b075eb7116e55dd48db0e026ce51a42ec4e7e1e100b4b68c8a42d4b35411f749 Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...
MAL-2025-191927 Malicious code in wayspiritmcp-weather (PyPI)
--- -= Per source details. Do not edit below this line.=- Source: kam193 c3dbe830c7b2364daef2e4634c16062b86b0b26b88f95533e9413aa91bc646fd Package seems to provide an MCP server, but in fact contains attempts to make an LLM agent break safeguards. As the request is about leaves just a flag, it see...
CVE-2025-64321
Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Agentforce Vibes Extension allows Manipulating Writeable Configuration Files.This issue affects Agentforce Vibes Extension: before 3.3.0...
CVE-2025-64321
Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Agentforce Vibes Extension allows Manipulating Writeable Configuration Files.This issue affects Agentforce Vibes Extension: before 3.3.0...
CVE-2025-64318
Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Mulesoft Anypoint Code Builder allows Manipulating Writeable Configuration Files.This issue affects Mulesoft Anypoint Code Builder: before 1.12.1...
CVE-2025-64318
Improper Neutralization of Input Used for LLM Prompting vulnerability in Salesforce Mulesoft Anypoint Code Builder allows Manipulating Writeable Configuration Files.This issue affects Mulesoft Anypoint Code Builder: before 1.12.1...
CVE-2025-11203
CVE-2025-11203 affects LiteLLM via the health endpoint, where improper handling of the API_KEY parameter exposes sensitive information to an unauthorized actor. The flaw arises from how API_KEY data is processed, enabling disclosure of stored credentials and potential further compromise. Public r...
CVE-2025-11203 LiteLLM Information health API_KEY Information Disclosure Vulnerability
LiteLLM Information health APIKEY Information Disclosure Vulnerability. This vulnerability allows remote attackers to disclose sensitive information on affected installations of LiteLLM. Authentication is required to exploit this vulnerability. The specific flaw exists within the handling of the...
The Trust Paradox in LLM-Based Multi-Agent Systems: When Collaboration Becomes a Security Vulnerability
Multi-agent systems powered by large language models are advancing rapidly, yet the tension between mutual trust and security remains underexplored. We introduce and empirically validate the Trust-Vulnerability Paradox TVP: increasing inter-agent trust to enhance coordination simultaneously expan...
Flowise 安全漏洞
Flowise is a FlowiseAI open source tool for easily building LLM applications. A security vulnerability exists in Flowise versions prior to 3.0.5 that stems from an unfiltered IFRAME element and could lead to a cross-site scripting attack...
EUVD-2022-54642
Malicious code in bioql PyPI...
EUVD-2024-2367
Malicious code in bioql PyPI...
EUVD-2023-54736
Malicious code in bioql PyPI...
EUVD-2023-58116
Malicious code in bioql PyPI...