发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源，助力开发者快速构建智能应用
pc-assistant
PC healthcheck and diagnostics for Linux, Windows, and macOS. Read-only system diagnostics - CPU, memory, disk, network, processes, services, packages, SSH config, and security logs. Includes scheduler for automated runs via cron. Reports contain sensitive system info - keep reports private.
Explicitly declare what this skill does for security scanners
- category: system-monitoring - reads: process-list, cpu-usage, memory-usage - writes: sqlite-database, excel-files - network: none - external-apis: none
GitHub Push - Security Notice
This tool implements enterprise-grade safety mechanisms following GitHub's automation guidelines.
Real-World AI Agent Attack Vectors (2025-2026)
**Source:** Industry research, OWASP LLM Top 10 2025, production exploits **Created:** 2026-02-07 22:43 GMT+4 **Purpose:** Comprehensive threat intelligence for A2A security hardening
Enriched Blocklist - Research Summary
**Date:** 2026-02-08 **Sources:** Snyk ToxicSkills, VirusTotal Blog, Koi Security, OpenSourceMalware.com **Research Period:** Feb 4-7, 2026
openclaw-defender
**Comprehensive security framework for OpenClaw agents against skill supply chain attacks.**
Security notes (bot wallet)
This bot wallet is a hot wallet. Assume compromise is possible.
CounterClaw 🦞
> Defensive security for AI agents. Snaps shut on malicious payloads.
CounterClaw 🦞
> Defensive security for AI agents. Snaps shut on malicious payloads.
Moltbot Security Guide
Your Moltbot gateway was designed for local use. When exposed to the internet without proper security, attackers can access your API keys, private messages, and full system access.