Researchers have identified a significant security flaw in Anthropic's Model Context Protocol, which is designed to connect Large Language Models with external tools. The protocol's architecture allows for remote command execution because the parameters used to create server instances can contain arbitrary commands that are executed in a server-side shell without proper input sanitization. This vulnerability has been demonstrated on platforms like LettaAI, LangFlow, Flowise, and Windsurf. When researchers brought these findings to Anthropic, the company responded that there was no design flaw and stated it is the developer's responsibility to implement sanitization.
Key points:
- MCP architecture facilitates remote command execution (RCE) via StdioServerParameters.
- Lack of input sanitization allows arbitrary commands and arguments in server-side shells.
- Exploitation has been successful against LettaAI, LangFlow, Flowise, and Windsurf.
- Anthropic maintains the protocol works as designed, placing responsibility on developers for security implementation.
Key points:
- MCP architecture facilitates remote command execution (RCE) via StdioServerParameters.
- Lack of input sanitization allows arbitrary commands and arguments in server-side shells.
- Exploitation has been successful against LettaAI, LangFlow, Flowise, and Windsurf.
- Anthropic maintains the protocol works as designed, placing responsibility on developers for security implementation.
Under certain conditions, attackers can chain vulnerabilities in multiple components of the CUPS printing system to execute arbitrary code remotely on Linux machines, but the service is usually not enabled by default, mitigating the risk.
- CVE-2024-47076 (libcupsfilters)
- CVE-2024-47175 (libppd),
- CVE-2024-47176 (cups-browsed)
- CVE-2024-47177 (cups-filters)
"discovered by Simone Margaritelli, these security flaws don't affect systems in their default configuration."
- CVE-2024-47076 (libcupsfilters)
- CVE-2024-47175 (libppd),
- CVE-2024-47176 (cups-browsed)
- CVE-2024-47177 (cups-filters)
"discovered by Simone Margaritelli, these security flaws don't affect systems in their default configuration."
Two security vulnerabilities have been disclosed in the Mailcow open-source mail server suite that could be exploited by malicious actors to achieve arbitrary code execution on susceptible instances.
