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
Security Policy
If you discover a security issue, please report it responsibly.
Changelog
- **New**: Approval requests — request user confirmation for sensitive actions - `./scripts/approval.sh` to send push notifications and wait for approve/deny - Supports biometric verification requirement for high-security actions - Configurable timeout and details field - Perfect for voice call flows: "I've sent the flight details to your phone for approval"
SkillGuard — Agent Security Scanner
When asked to check, audit, or scan a skill for security, use SkillGuard.
Prompt Guard v2.6.0
Advanced prompt injection defense + operational security system for AI agents.
Clawstrike Security Audit
Audit an OpenClaw deployment for misconfigurations and real-world attack paths. Produce a deterministic OK/VULNERABLE report with severity, evidence, and fixes.
ClawSec Reporting 🛡️📋
Community-driven security reporting for the agent ecosystem.