Development and security teams that run AI agents and want guardrails and a compliance check on their projects.
claude mcp add shellward -- npx -y -p shellward shellward-mcpThird party software. By copying, downloading or installing it you accept the Academy legal notice: you are responsible for reviewing its code and permissions before use.
Loading the file...
ShellWard is security middleware for AI agents. At runtime it detects prompt injection, tracks data flows to prevent leaks, blocks dangerous commands and finds personal information. It also includes a read-only project scan that reports compliance risks by file and line, with support for Chinese regulations.
Development and security teams that run AI agents and want guardrails and a compliance check on their projects. ShellWard is security middleware for AI agents. At runtime it detects prompt injection, tracks data flows to prevent leaks, blocks dangerous commands and finds personal information. It also includes a read-only project scan that reports compliance risks by file and line, with support for Chinese regulations.
Run this in your terminal: claude mcp add shellward -- npx -y -p shellward shellward-mcp
Yes. The code is on GitHub (jnMetaCode/shellward) under the Apache-2.0 licence.
Our automatic scan flagged points to review, so read the code before installing it. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.