Scan-Skill Mode

Secure your agentic coding workflow by scanning skills before installation and after deployment

Skill Security Scan (scan-skill)

scan-skill adds a security gate for skills used by agentic coding tools. It can scan a remote skill before installation and scan a local skill folder already installed on your machine.

Motivation Skills execute with user-level permissions. That means a malicious skill can attempt credential theft, persistence, remote payload execution, or agent manipulation. This feature is designed to reduce that supply-chain risk by providing a structured, repeatable security scan before trust is granted.

How it works

1. Input handling:

   • Remote input: scans supported remote sources (currently GitHub and ClawHub/ClawdHub hosts), a ZIP archive URL, or a raw SKILL.md URL.

   • Local input: accepts a local directory path, recursively packages it in-memory, and requires a SKILL.md file.

2. Safe ingestion:

   • Enforces size and structure limits.

   • Skips symlinks and non-text/binary content for analysis stages.

   • Preserves SKILL.md as the primary manifest.

3. Multi-layer detection:

   • Static layer: known malicious patterns and indicators.

   • Behavioral layer: suspicious code behavior/data-flow patterns.

   • Semantic layer (LLM): context-aware reasoning, false-positive review at finding level, and final narrative summary.

4. Result output:

   • Returns verdict (BENIGN, WARNING, SUSPICIOUS, MALICIOUS), findings, evidence, severity, and optional analysis summary.

   • Uses hash-based caching to reuse prior scan results for identical skill content.

Usage

To check what options are available, run:

npx @mobb.ai/cli@latest scan-skill --help

Here is the output of the help file:

mobbdev scan-skill

Scan an OpenClaw/ClawHub skill for security threats.

Options:
  --url       URL or local directory of the skill to scan (GitHub repo, ZIP archive, raw SKILL.md, or folder
              containing SKILL.md)                                                                   [string] [required]
  --api-key   Mobb authentication api-key                                                                       [string]
  --ci        Run in CI mode, prompts and browser will not be opened                           [boolean] [default: false]
  --help      Show help                                                                                        [boolean]

Examples:
  npx mobbdev@latest scan-skill --url            Scan an OpenClaw/ClawHub skill for security threats
  https://github.com/user/my-skill
  npx mobbdev@latest scan-skill --url            Scan a local skill directory that contains SKILL.md
  ./my-skill-folder

CLI usage

# Remote GitHub skill
npx @mobb.ai/cli@latest scan-skill --url https://github.com/user/my-skill

# Remote ClawHub skill
npx @mobb.ai/cli@latest scan-skill --url https://clawhub.ai/user/skill-slug

# Local installed skill folder (must contain SKILL.md)
npx @mobb.ai/cli@latest scan-skill --url /path/to/skills/my-skill

# Non-interactive CI mode
npx @mobb.ai/cli@latest scan-skill --url /path/to/skills/my-skill --ci

Note: local scanning expects a directory containing SKILL.md, not a direct SKILL.md file path. A raw SKILL.md is accepted only as a remote URL.