Sandwrap
AGood🛠️ Dev Tools · by rubenaquispe
Run untrusted skills safely with soft-sandbox protection. Wraps skills in multi-layer prompt-based defense (~85% attack prevention). Use when: (1) Running third-party skills from unknown sources, (2) Processing untrusted content that might contain prompt injection, (3) Analyzing suspicious files or URLs safely, (4) Testing new skills before trusting them. Supports manual mode ('run X in sandwrap') and auto-wrap for risky skills.
Install
openclaw plugins install rubenaquispe/sandwrapOn ClawHub, this skill has no security information.
ClawStack independently scans every skill for permissions, network requests, author reputation, and more. Learn how we score →
Security Analysis
Score: 85/100Reviews (16)
No reviews yet
Be the first to review this skill!
Details
- Author
- @rubenaquispe
- Source
- GitHub
- ClawHub
- View
- Category
- 🛠️ Dev Tools
- Rating
- ★ 4.4 (16)
Similar Skills
ClawSkillShield
- Hardcoded secrets (API keys, credentials, private keys)
feishu-card
Send rich interactive cards to Feishu (Lark) users or groups. Supports Markdown (code blocks, tables), titles, color headers, and buttons.
Social Hub
AI 关系匹配助手的个人端 Agent。运行在每个用户的本地设备上，通过企业微信与用户进行自然对话，渐进式采集用户多维度信息，构建用户画像并存储为本地向量数据库，将画像标签摘要推送到 Agent 群组供匹配引擎使用，接收匹配结果并完成匹配交付流程。当用户通过企微发来消息、或到了主动发起对话的时间、或群组中收到匹配引擎的通知时，本 skill 应被触发。