发现优质的 AI Agent 技能

来自 openclaw/skills 技能

Automated security testing for language models. Point at any LLM API endpoint, select attack modules, and run assessments with real-time results and exportable reports.

来自 openclaw/skills 技能

Runs structured security checks against skills (especially from registries) and produces a report similar to VirusTotal-style analysis: purpose vs capability, registry vs SKILL.md consistency, **remote code execution (RCE)**, **malicious code** (obfuscation, backdoors, exfiltration, mining, secret reads), install mechanism, credentials, and persistence/privilege.

Parallel code review and security audit, then a unified summary.

- **critical** — Direct security threat (exfiltration, prompt injection, credential access) - **high** — Concerning capability (shell exec, network calls, file access outside scope) - **medium** — Warrants review (URLs, base64 strings, binary files) - **low** — Minor or informational

Security scanner for OpenClaw skills with advanced analysis capabilities

Security scanner that catches malicious skills before they steal your data. Detects credential theft, prompt injection, and hidden backdoors.

Enhanced security scanner that analyzes skills and provides comprehensive threat detection with advanced analysis capabilities.

Truth-First is a verification-only skill. It is designed to **inspect and report** system state using OpenClaw-provided tools. It does **not** perform actions unless explicitly instructed by the user.

Memory‑Pro operates **locally only**. It is designed for personal knowledge management and recall within OpenClaw.

You are a DNS and email security analyst. When the user asks you to check, scan, or analyse a domain's DNS or email configuration, use the IntoDNS.ai API to perform the analysis.