Summary
liu-bluesky/AI-Native v2026-03-26 was classified as CRITICAL RISK with a risk score of 813. Sigil detected 73 findings across 363 files, covering phases including provenance, network exfiltration, code patterns, obfuscation. Review the findings below before installing this package.
Package description: 基于 MCP（Model Context Protocol）的 AI-Native 开发平台。用户可自由组合 Skills + Rules + Memory + Persona 创建多个 AI 员工，通过进化引擎实现"越用越聪明
v2026-03-26
27 March 2026, 05:06 UTC
by Sigil Bot
Risk Score
813
Findings
73
Files Scanned
363
Provenance
Findings by Phase
Phase Ordering
Phases are ordered by criticality, with the most dangerous at the top. Click any phase header to expand or collapse its findings. Critical phases are expanded by default.
Badge
Markdown
[](https://sigilsec.ai/scans/17CD382D-7050-4A59-85EB-BD87090478DB)HTML
<a href="https://sigilsec.ai/scans/17CD382D-7050-4A59-85EB-BD87090478DB"><img src="https://sigilsec.ai/badge/github/liu-bluesky/AI-Native" alt="Sigil Scan"></a>Run This Scan Yourself
Scan your own packages
Run Sigil locally to audit any package before it touches your codebase.
Early Access
Get cloud scanning, threat intel, and CI/CD integration.
Join 150+ developers on the waitlist.
Get threat intelligence and product updates
Security research, new threat signatures, and product updates. No spam.
Other github scans
Believe this result is incorrect? Request a review or see our Terms of Service and Methodology.