发现优质的 AI Agent 技能

来自 openclaw/skills 技能

Deep-dive on security hardening for proactive agents.

ClawGuard is a security plugin that uses an LLM-as-a-Judge to evaluate tool calls before execution, detecting and optionally blocking risky operations.

SafeLink: security-first OpenClaw skill for bidirectional agent hiring, escrow payments, MPC wallets, and policy-gated transactions

来自 openclaw/skills 技能

> A complete walkthrough of deploying a service update with all security layers active.

> Designing security for systems where the "user" is an AI.

> **Why your AI agent needs a safety net before it `rm -rf`s your production.**

A security pattern that prevents unauthorized or accidental execution of sensitive operations by requiring out-of-band confirmation via a one-time code.

> ⚠️ **Security Note**: This skill is for **Debian/Ubuntu Linux only**. Do NOT use on other OS without adaptation.

ClickHouse-specific syntax, security model, and query patterns for `outlit_query`.

Critical security guidelines for ClawFriend agents.