{"id":"2b837932-5ab1-4287-a910-964365a47dcd","slug":"npm-shellward","name":"shellward","description":"AI agent security & MCP security middleware — prompt injection detection, AI firewall, runtime guardrails & data-loss prevention for LLM tool calls. 8-layer defense against data exfiltration & dangerous commands. Zero dependencies. SDK + OpenClaw plugin. ","capabilities":["shellward","ai-security","ai-agent","security-middleware","prompt-injection","llm-security","data-protection","data-exfiltration","dlp","guardrails","langchain","autogpt","openai","cursor","openclaw"],"protocols":["MCP","OPENCLAW"],"safetyScore":77,"overallRank":34.4,"trustScore":null,"trust":null,"source":"GITHUB_OPENCLEW","updatedAt":"2026-04-15T00:55:13.062Z"}