Free AI agent skill security scanner. Scan SKILL.md, MCP configs, and system prompts for credential theft, prompt injection, zero-width character attacks, and ClawHavoc indicators. Supports OpenClaw, Claude Code, Cursor, and Codex. No signup required.
Run the underlying MCP server directly — without Agent-CoreX routing.
npx -y skillssafe-mcpAgent-CoreX intelligently routes which tools from GUCCI-atlasv/skillssafe-mcp your AI agent actually needs per request — reducing token usage and cost.
agent-corex.json
{
"mcpServers": {
"skillssafe-mcp": {
"command": "npx",
"args": [
"-y",
"skillssafe-mcp"
]
}
}
}Connect in 2 minutes. Only pay for the tools your agent actually uses.
Recommended: intelligent tool routing, lower costs
uvx agent-corex mcp add skillssafe-mcpAgent-CoreX selects only the tools your agent needs, cutting token usage by up to 60%.
Use GUCCI-atlasv/skillssafe-mcp directly without routing
npx -y skillssafe-mcpNew to Agent-CoreX? View setup guide →