发现优质的 AI Agent 技能

Verify AI agents, check trust scores (0-100), discover marketplace agents, and apply guardrails for security and compliance.

Verify AI agents, check trust scores (0-100), discover marketplace agents, and apply guardrails for security and compliance.

Scan OpenClaw skills for security threats before they compromise your system.

Context graph analysis, runtime audit log correlation with CVE findings, and vulnerability analytics queries.

Look up MCP servers in the 427+ server security metadata registry, assess skill file trust, and run pre-install marketplace checks.

Evaluate AI infrastructure scan results against security frameworks and enforce policy-as-code rules. Generate SBOMs in standard formats.

Onnex-owned, security-reviewed fork of **youtube-ultimate** by globalcaos.

**Audit Date:** February 14, 2026 **Auditor:** Claude Opus 4.6 (Anthropic) **Kit Version:** 2.0.2 **SDK Version:** torchsdk 3.7.23 **On-Chain Program:** `8hbUkonssSEEtkqzwM7ZcZrD9evacM92TcWSooVF4BeT` (V3.7.8)

**Audit Date:** February 21, 2026 **Auditor:** Claude Opus 4.6 (Anthropic) **SDK Version:** 3.7.30 **On-Chain Program:** `8hbUkonssSEEtkqzwM7ZcZrD9evacM92TcWSooVF4BeT` (V3.7.10) **Language:** TypeScript

**Date:** February 27, 2026 | **Auditor:** Claude Opus 4.6 (Anthropic) | **Version:** V3.7.10 Production

**Audit Date:** February 27, 2026 **Auditor:** Claude Opus 4.6 (Anthropic) **Bot Version:** 4.0.2 **Kit Version:** 2.0.0 **SDK Version:** torchsdk 3.7.22

**Audit Date:** February 28, 2026 **Auditor:** Claude Opus 4.6 (Anthropic) **Bot Version:** 2.0.1 **SDK Version:** torchsdk 3.7.23 **On-Chain Program:** `8hbUkonssSEEtkqzwM7ZcZrD9evacM92TcWSooVF4BeT` (V3.7.8)