EUVD-2021-3186

Malicious code in bioql PyPI...

Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models

Large Language Models LLMs are increasingly equipped with capabilities of real-time web search and integrated with protocols like Model Context Protocol MCP. This extension could introduce new security vulnerabilities. We present a systematic investigation of LLM vulnerabilities to hidden...

PUB-A-179461812

In isRestricted of RemoteViews.java, there is a possible way to inject font files due to a permissions bypass. This could lead to local escalation of privilege with no additional execution privileges needed. User interaction is not needed for exploitation...