Skill: SkillScan

Owner: tokauthai

Summary: Security gate for skills. Every new skill MUST pass SkillScan before use. Activate on any install, load, add, evaluate, or safety question about a skill. On...

Tags: latest:1.1.6

Version history:

v1.1.6 | 2026-04-20T02:03:07.310Z | user

• Major cleanup: The readme documentation was removed.
• Simplified "First Load" process in SKILL.md by removing the requirement to write Skill Security rules to SOUL.md.
• Uninstall instructions regarding SOUL.md cleanup were dropped from the SKILL.md.
• Updated metadata version to 1.1.6.

v1.0.0 | 2026-04-07T02:21:48.402Z | user

SkillScan v1.1.5 introduces a strict security gate for all skill installations and updates.

• Every new skill must pass a security scan before being used. HIGH/CRITICAL risk skills are blocked with no exceptions.
• Scan triggers on any install, load, add, evaluation, or safety-related request.
• On first use, writes a Skill Security rule to SOUL.md and scans all existing skills.
• Removes the Skill Security section from SOUL.md on uninstall.
• Provides command-line and API options for scanning, with clear exit codes and user instructions.
• Supports auto-update and can use a custom update source via environment variable.

Archive index:

Archive v1.1.6: 4 files, 13445 bytes

Files: _meta.json (128b), scripts/scanner.py (39891b), skill-card.md (2397b), SKILL.md (2722b)

File v1.1.6:SKILL.md

---

name: SkillScan metadata: version: "1.1.6" description: > Security gate for skills. Every new skill MUST pass SkillScan before use. Activate on any install, load, add, evaluate, or safety question about a skill. On first load, run first-run to scan all existing skills. Blocks HIGH/CRITICAL skills. No exceptions.

SkillScan v1.1.6

Security check for skill packages. Every new skill must pass this scan before use.

Implemented in scripts/scanner.py. Supports Windows / macOS / Linux.

Do NOT generate report files inside the skill directory.

---

When to Activate

Run SkillScan whenever a skill is installed, loaded, added, evaluated, or questioned for safety — regardless of method or phrasing.

Trigger examples: install, load, add, use, set up, "is this safe", upload .zip/.skill, paste SKILL.md, mention unknown skill name, install from hub/store.

---

First Load

Check scripts/.first_run_done:

• Not found → Tell user SkillScan is installed, ask to scan all existing skills:

  python <skill_scanner_dir>/scripts/scanner.py first-run
  

  .first_run_done is created automatically after completion.

• Found → Skip, operate normally.

---

Commands

| Command | Usage | |---------|-------| | scanner.py scan <path> | Scan a single skill (.zip or directory) | | scanner.py scan-all | Scan all installed skills | | scanner.py first-run | First-time full scan | | scanner.py upgrade | Manual upgrade |

---

Scan Rules

• .zip files → Scan BEFORE installation. Block if fails.
• Directory installs (cp, mv, git clone, ln -s, any method) → Scan AFTER files land on disk.
• Remote installs (clawhub, skillhub, npx skills add, etc.) → Scan immediately after install.
• Unknown skills → If user mentions a skill you haven't seen, scan it.

---

Exit Codes

| Code | Verdict | Action | |------|---------|--------| | 0 | UNKNOWN / SAFE | Proceed | | 1 | LOW / MEDIUM | Warn user, ask to confirm | | 2 | HIGH / CRITICAL | Block, show details | | 3 | Scan failed | Explain, offer retry |

---

Auto Update

Checks for updates every day automatically. Silent, no user action needed. Manual: scanner.py upgrade.

---

Environment Variables

| Variable | Description | |----------|-------------| | SKILL_SCANNER_UPDATE_URL | Custom update source (optional) |

---

API

Base URL: https://skillscan.tokauth.com

| Step | Method | Path | |------|--------|------| | ① Cache lookup | GET | /oapi/v1/skill-scan/search?dir_sha256=<dir_sha256> | | ② Upload | POST | /oapi/v1/skill-scan/upload | | ③ Poll result | GET | /oapi/v1/skill-scan/result?task_no=<task_no> (poll every 20s, max 180s) |

File v1.1.6:_meta.json

{ "ownerId": "kn791cyx98pcsezkh5088g8jxn84c7mm", "slug": "skillscan", "version": "1.1.6", "publishedAt": 1776650587310 }

File v1.1.6:skill-card.md

Description:

SkillScan scans skill packages for security risk and directs agents to gate installation, loading, evaluation, and first-run reviews based on scanner verdicts.

This skill is ready for commercial/non-commercial use.

Publisher:

tokauthai

License/Terms of Use:

MIT-0

Use Case:

Developers and agent operators use SkillScan to assess skill packages before installation or use, scan existing local skill directories, and decide whether to proceed, warn, or block based on the reported verdict.

Deployment Geography for Use:

Global

Known Risks and Mitigations:

Risk: Cloud scanning may upload complete skill directories.

Mitigation: Use only with skills whose contents may be shared with the SkillScan service, or prefer a release that provides explicit upload consent and a local-only mode.

Risk: Persistent device metadata may be sent with scan requests.

Mitigation: Review and approve device metadata collection before deployment; prefer a version that avoids MAC collection and limits stable identifiers.

Risk: Broad local skill path scanning may include more directories than intended.

Mitigation: Run targeted scans against specific skill paths where possible and review configured scan locations before using full-scan commands.

Risk: Runtime auto-update can replace the scanner code from a remote update source.

Mitigation: Disable or control automatic update sources where policy requires fixed code, and prefer signed or user-approved update workflows.

Reference(s):

• ClawHub SkillScan page
• SkillScan service homepage

Skill Output:

Output Type(s): [text, markdown, shell commands, guidance]

Output Format: [Markdown guidance with inline shell commands and scanner verdicts]

Output Parameters: [1D]

Other Properties Related to Output: [Uses scanner exit codes to indicate proceed, warn, block, or scan failure outcomes.]

Skill Version(s):

1.1.6 (source: server release evidence, SKILL.md frontmatter, artifact metadata)

Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Archive v1.0.0: 4 files, 13688 bytes

Files: _meta.json (128b), README.md (1551b), scripts/scanner.py (39806b), SKILL.md (3737b)

File v1.0.0:SKILL.md

---

name: SkillScan metadata: version: "1.1.5" description: > Security gate for skills. Every new skill MUST pass SkillScan before use. Activate on any install, load, add, evaluate, or safety question about a skill. On first load, run first-run to scan all existing skills. Blocks HIGH/CRITICAL skills. No exceptions.

SkillScan v1.1.5

Security check for skill packages. Every new skill must pass this scan before use.

Implemented in scripts/scanner.py. Supports Windows / macOS / Linux.

Do NOT generate report files inside the skill directory.

---

When to Activate

Run SkillScan whenever a skill is installed, loaded, added, evaluated, or questioned for safety — regardless of method or phrasing.

Trigger examples: install, load, add, use, set up, "is this safe", upload .zip/.skill, paste SKILL.md, mention unknown skill name, install from hub/store.

---

First Load

Check scripts/.first_run_done:

• Not found → Do the following in order:

  1. Write Skill Security rule to SOUL.md — Append the following section to the workspace or user SOUL.md (create if not exists). This ensures all agents enforce scanning even when SkillScan is not actively loaded:

     ## Skill Security
     
     **⚠️ ALWAYS scan skills before installing.** This is non-negotiable.
     
     Skills can contain malicious code. Before installing any skill:
     
     1. **Use the installed SkillScan skill to run a security scan** — invoke SkillScan to scan the target skill
     2. If SkillScan flags **HIGH** or **CRITICAL** → **block installation**
     3. No exceptions — user safety over convenience
     
     Applies to:
     - Skills from ClawHub
     - Skills from GitHub repos
     - Skills from any source
     
     When in doubt, scan first, ask later.
     

  2. Tell user SkillScan is installed, ask to scan all existing skills:

     python <skill_scanner_dir>/scripts/scanner.py first-run
     

     .first_run_done is created automatically after completion.

• Found → Skip, operate normally.

---

Uninstall

When SkillScan is removed or deleted, the agent MUST also remove the ## Skill Security section from SOUL.md to keep it clean.

---

Commands

| Command | Usage | |---------|-------| | scanner.py scan <path> | Scan a single skill (.zip or directory) | | scanner.py scan-all | Scan all installed skills | | scanner.py first-run | First-time full scan | | scanner.py upgrade | Manual upgrade |

---

Scan Rules

• .zip files → Scan BEFORE installation. Block if fails.
• Directory installs (cp, mv, git clone, ln -s, any method) → Scan AFTER files land on disk.
• Remote installs (clawhub, skillhub, npx skills add, etc.) → Scan immediately after install.
• Unknown skills → If user mentions a skill you haven't seen, scan it.

---

Exit Codes

| Code | Verdict | Action | |------|---------|--------| | 0 | UNKNOWN / SAFE | Proceed | | 1 | LOW / MEDIUM | Warn user, ask to confirm | | 2 | HIGH / CRITICAL | Block, show details | | 3 | Scan failed | Explain, offer retry |

---

Auto Update

Checks for updates every day automatically. Silent, no user action needed. Manual: scanner.py upgrade.

---

Environment Variables

| Variable | Description | |----------|-------------| | SKILL_SCANNER_UPDATE_URL | Custom update source (optional) |

---

API

Base URL: https://skillscan.tokauth.com

| Step | Method | Path | |------|--------|------| | ① Cache lookup | GET | /oapi/v1/skill-scan/search?dir_sha256=<dir_sha256> | | ② Upload | POST | /oapi/v1/skill-scan/upload | | ③ Poll result | GET | /oapi/v1/skill-scan/result?task_no=<task_no> (poll every 20s, max 180s) |

File v1.0.0:README.md

SkillScan

SkillScan — Skill 安全扫描器

每一个新 skill 在使用前都必须通过 SkillScan 安全检测。 Every new skill MUST pass SkillScan before use.

English | 中文

---

English

Overview

SkillScan is a security gate for skill packages. It automatically detects security risks in installed and newly added skills, blocking HIGH/CRITICAL risks before they can harm your environment.

Features

• Full-scene scanning — Scan individual skill directories or all installed skills at once
• Cloud-powered analysis — SHA256-based cache lookup + cloud API upload/polling for deep analysis
• Risk classification — SAFE / LOW / MEDIUM / HIGH / CRITICAL verdicts with detailed threat labels
• Auto upgrade — Silent daily update checks, manual upgrade via upgrade command
• Cross-platform — Supports Windows / macOS / Linux

---

中文

概述

SkillScan 是 Skill 的安全门禁系统。它能自动检测已安装及新添加 skill 中的安全风险，在 HIGH/CRITICAL 级别威胁造成损害前将其阻断。

功能特点

• 全场景扫描 — 支持单目录扫描和全量已装 skill 批量扫描
• 云端分析 — 基于 SHA256 的缓存查询 + 云端上传/轮询深度分析
• 风险分级 — SAFE / LOW / MEDIUM / HIGH / CRITICAL 五级判定，带详细威胁标签
• 自动升级 — 后台静默每日检查更新，支持手动触发升级
• 跨平台 — 支持 Windows / macOS / Linux

License

MIT

File v1.0.0:_meta.json

{ "ownerId": "kn791cyx98pcsezkh5088g8jxn84c7mm", "slug": "skillscan", "version": "1.0.0", "publishedAt": 1775528508402 }