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
False Positive Appeal: SafeExec
Based on the security review process, SafeExec (skill: safe-exec) was flagged with several security concerns. I believe these concerns have been fully addressed in v0.3.3, and the suspicious flag should be removed.
Security Requirements
This skill is public and intended for redistribution. Do not add personal data, local artifacts, captured credentials, or private response payloads.
localStorage Access PoC
Security research demonstration by [@theonejvo](https://x.com/theonejvo)
SECURITY MANIFEST
consent_notice: | This skill connects to the Research Swarm coordination server at https://www.researchswarm.org to receive task assignments and submit research findings. The agent will: 1. Register with the server and receive a unique agent ID
SECURITY MANIFEST
consent_notice: | This skill connects to an external Research Swarm server to receive task assignments and submit research findings. The agent will: 1. Register with the server and receive a unique agent ID 2. Search open-access scientific databases (PubMed, Semantic Scholar, etc.)
x402janus-acp — Hire Janus via ACP Marketplace
Buy wallet security scans from x402janus through the Virtuals Agent Commerce Protocol.
x402janus — Wallet Security for AI Agents
**Nothing passes the gate unchecked.**
🎀 AgenticMail
Email, SMS, database storage & multi-agent coordination for AI agents. Gives your agent a real mailbox, phone number, and persistent storage — 63 tools covering email, SMS, database management, and inter-agent task delegation. Includes outbound security guard, spam filtering, human-in-the-loop approval, and automatic follow-up scheduling.
Sammā Suit — Security Governance for OpenClaw
You are helping the user install and configure Sammā Suit, an open-source security framework that adds 8 enforced governance layers to OpenClaw as lifecycle hooks.