jnMetaCode/shellward
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + OpenClaw plugin.
Platform-specific configuration:
{
"mcpServers": {
"shellward": {
"command": "npx",
"args": [
"-y",
"shellward"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Loading reviews...