AI 技能注册表

Drift detection + baseline integrity guard for agent workspace files with automatic alerting support

审计本地 openclaw 的安全配置与运行暴露面。用于检查、验证、解释和总结当前机器或沙箱中的 openclaw 相关安全设置，包括代理配置、sandbox 配置、docker 端口暴露、gateway 检查、文件权限、workspace symlink 风险、本地监听端口以及整体本地安全状态。

Guide for proper chemical waste disposal by waste container color

Enterprise AI security scanner combining static code analysis, runtime guards, ClamAV integration, and tamper-proof audit logging to detect threats and enfor...

Compare draft agreements, highlight risky clause changes, and generate a negotiation checklist with plain-language explanations.

Collects and summarizes Korean security news hourly from 11 sources using Gemini API, then publishes to Notion and optionally to Tistory blog.

Execute zero-fee direct token swaps and manage stop-loss, take-profit, and portfolio tracking on Base chain via Uniswap V3 with self-custodial security.

Automatically redacts API keys, tokens, and secrets from workspace logs and memory files.

Trust and evidence verification engine for claims, sources, screenshots, profiles, offers, and suspicious messages. Use whenever the user asks whether someth...

Simple local security check (firewall, updates, ssh status) without external dependencies.

Determine whether an incident in a clinical trial is a "major deviation" or "minor deviation". Function: Automatically classify protocol deviations in clinic...

Verify agent-to-agent communication against session type protocols. Mathematical proofs, not trust.

MTProto 2.0 protocol implementation guide for Telegram backend development. Use when implementing MTProto encryption, handshake, message serialization, or bu...

OpenClaw Gateway Guardian - Automatic monitoring, protection, and restart of OpenClaw Gateway service. Prevents gateway from stopping, crashing, or disappear...

管理Clash/mihomo代理环境，支持安装、启停代理、订阅管理、Web面板操作、Tun模式配置、升级内核等常用功能。触发场景：用户提到clash、mihomo、代理、clashctl、clashon、clashoff、clashui、订阅更新等关键词时使用。

Bug Bounty 猎人 - 自动扫描漏洞、生成报告、追踪奖励。适合：安全研究员、白帽子。

Provides time-limited, self-revoking SSH access for AI agents using certificate TTL, user expiry, forced command restrictions, and scheduled automated cleanup.

萤石语音广播技能。支持本地音频文件上传或文本转语音，实现语音内容下发到设备播放。 Use when: 需要向萤石设备发送语音通知、广播、提醒等音频内容。 ⚠️ 安全要求：必须设置 EZVIZ_APP_KEY 和 EZVIZ_APP_SECRET 环境变量，使用最小权限凭证。

梳理数据保留周期、落盘位置、清理责任与过期处置建议。；use for data-retention, governance, privacy workflows；do not use for 替代正式合规意见, 隐瞒敏感存储位置风险.

AI自我安全防护系统v2。多层防御：提示注入、身份冒充、系统提示泄露、 过度代理、供应链攻击、凭证窃取、恶意代码、敏感数据泄露、行为异常检测。 触发词：安全防护、身份验证、prompt injection、system prompt、 权限升级、MCP安全、self-safety-guard、安全检查。

Securely interact with Bitwarden password manager via the bw CLI. Covers authentication (login/unlock/logout), vault operations (list/get/create/edit/delete...

Prompt injection detection and security scanning for OpenClaw agents. Installs the ai-sentinel plugin via OpenClaw CLI, configures plugin settings, and offer...

Analyze and optimize internal link structure to improve site architecture, distribute page authority, and fix orphan pages. Use when the user asks to "fix in...

Secure AI agent wallets via Sigil Protocol. 3-layer Guardian validation on 6 EVM chains.