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
Enhanced Security Features - Summary
The Prompt Injection Protection skill has been significantly enhanced with real-time security alerting capabilities to protect against various threats when processing external content.
Auto-Learning Security System - Complete Implementation
The Prompt Injection Protection skill has been enhanced with advanced machine learning capabilities that enable autonomous learning, adaptation, and self-improvement to protect against evolving prompt injection and exploitation threats.
Security Patterns Reference
Deep-dive on security hardening for proactive agents.
Security Model
The router delegates to two sub-skills (datetime and scheduling) based on user intent. All tools share the same MCP server binary and security model.
Security Model
The router delegates to two sub-skills (datetime and scheduling) based on user intent. All tools share the same MCP server binary and security model.
🔧 Security Scan 修复说明
**版本**: 1.0.2 **日期**: 2026-03-04 **修复人**: 虾哥 AI Assistant
glab api - Advanced API Access
> ⚠️ **Security Warning**: This command provides unrestricted GitLab API access with your authenticated token. A compromised or overly-permissive token can delete projects, modify settings, expose secrets, and perform other destructive operations.
Skill Guard v2 🛡️
Advanced security scanner for OpenClaw skills. Detects malicious code, prompt injection, supply chain attacks, data exfiltration, credential theft, and more — with smart domain analysis, tamper detection, and actionable recommendations.
q-kdb-code-review
AI-powered code review for Q/kdb+ — catch bugs, performance issues, and security vulnerabilities in the most terse language in quantitative finance.