# Scan Repo

> Scan a repository or directory for security threats using Sigil. Use when auditing AI agent code, reviewing cloned repositories, checking dependencies, or analyzing suspicious packages. Auto-invoke when users clone repos or install packages from untrusted sources. Trigger phrases (English): 'is this safe to install', 'scan this skill', 'vet this MCP server', 'check this package before installing', 'is this repo safe', 'audit this code'. Trigger phrases (Chinese): '安全扫描', '这个插件安全吗', '这个技能安全吗', '扫描一下', '安装前检查'.

- Skill: `nomarj/scan-repo` (Agent Skill)
- Install (CLI): `npx skillmds@latest add nomarj/scan-repo`
- Raw SKILL.md: https://api.skillmd.com/api/skills/nomarj/scan-repo/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: nomarj (https://skillmd.com/u/nomarj)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/nomarj/scan-repo

---


# Security Scan with Sigil

Scan the target repository/directory for malicious patterns:

1. Run Sigil scan on the target path
2. Review detected threats (install hooks, eval/exec, network exfil, credentials)
3. Show risk score and verdict
4. Recommend approve/reject based on findings

**Usage:**
```bash
sigil scan <path>
```

**Output interpretation:**
- CLEAN (score 0): Safe to use
- LOW RISK (1-9): Review findings
- MEDIUM RISK (10-24): Manual review required
- HIGH RISK (25-49): Block unless override
- CRITICAL (50+): Block, no override

Present findings clearly and recommend next steps.