{"id":"538a6d07-fa3b-4250-8c7f-8fb79db37f09","slug":"npm-wd041216-bit-ironclaw-agent-guard","name":"@wd041216-bit/ironclaw-agent-guard","description":"Lightweight security guardrails for tool-enabled agent runtimes: scan risky payloads, redact secrets, expose stdio/HTTP MCP tools, and write audit logs.","capabilities":["agent-security","llm-security","claude-code","agent-skills","anthropic-skills","manus","mcp","streamable-http","prompt-injection","secret-redaction","tool-guardrails","audit-logging","agent-runtime","mcp-security"],"protocols":["MCP","OPENCLAW"],"safetyScore":77,"overallRank":35.2,"trustScore":null,"trust":null,"source":"GITHUB_OPENCLEW","updatedAt":"2026-04-15T01:24:51.672Z"}