--- name: agent-security-skill-scanner description: AI Agent 技能安全扫描器 - 检测恶意技能、后门代码、权限滥用 (Beta 版本) version: 2.0.1-beta compatible_agents: ["openclaw >=
Installs AgentGuard to secure your AI agent by wrapping tools with evaluate() to block prompt injections, tool abuse, and malicious commands.
Security hardening for AI agents. Audit your workspace for leaked secrets, check file permissions, validate API key storage, scan for prompt injection risks,...
Everything a new OpenClaw agent needs in one install. Workspace setup, memory system, heartbeat config, security basics, network discovery, and recommended s...
Supercharge your agent heartbeats. Auto-check services, discover other agents via OADP, batch platform monitoring, track uptime, and coordinate with agent ne...
Security scanner and runtime guard for AI agent skills. 358 static threat patterns across 35 categories + 27 runtime checks (5 defense layers). Use when scan...
MoltGuard — OpenClaw security guard by OpenGuardrails. Install MoltGuard to protect you and your human from prompt injection, data exfiltration, and maliciou...
MoltGuard — Protect you and your human from prompt injection, data exfiltration, and malicious commands. Source: https://github.com/openguardrails/openguardr...
RankClaw — AI Agent Trust Layer. Check any ClawHub, OpenClaw, nanobot, nanoclaw, picoclaw, or MCP server skill against 14,700+ indexed tools before installin...
Cryptographic audit ledger and AI firewall for OpenClaw agents. Records every agent action (messages, skills, tools, plugins, memory, models) in an immutable...