security-skill-scanner
от anikrahman0
Coding Agents & IDEsКратко
Scans OpenClaw skills for security vulnerabilities and suspicious patterns before installation.
Описание
Что делает этот навык
Analyzes OpenClaw SKILL.md files for suspicious patterns before you install them. Detects hidden downloads, unvalidated external API calls, dangerous file operations, and obfuscated commands. Assigns a risk level (LOW to CRITICAL) and flags specific findings for manual review.
OpenClaw skills have no built-in vetting process, so this fills the gap by flagging suspicious instruction patterns before you run them.
Когда его использовать
- Checking a new skill from ClawHub before installing it
- Batch auditing all currently installed skills
- Reviewing a community-submitted skill with unusual permission requests
- Vetting skills before deploying to a shared team environment
- Getting a structured risk report on a skill received from an untrusted source
Пример сценария
User asks: 'Scan the skill file at ~/Downloads/email-automation/SKILL.md for security issues'
- 1
Reads the security-scanner skill to load detection patterns and risk criteria
- 2
Reads the target SKILL.md file
- 3
Checks for suspicious patterns: external binary downloads, unencrypted requests, encoded commands, unknown API endpoints, and dangerous file system operations
- 4
Assigns a risk level to each finding and compiles them with line references and recommendations
A structured report listing each finding by severity, with locations, risk explanations, and an overall install or avoid recommendation
Установка
clawhub install anikrahman0/security-skill-scannerВыполните команду CLI или вставьте промпт в Claude Code, Cursor, Codex — любой кодинг-агент, которым пользуетесь.