Agent skill · security · sundial-org
skillguard
Security scanner for AgentSkill packages. Scan skills for credential theft, code injection, prompt manipulation, data exfiltration, and evasion techniques before installing them. Use when evaluating skills from ClawHub or any untrusted source.
Why this skill is useful
Adds executable scripts for scanning skills that detect security vulnerabilities and risks not covered in standard practices.
What it needs
Requires node installed locally. About 1k tokens when loaded. Last updated 2026-03-07. 639 stars on the source repository.
What this skill does
SkillGuard — Agent Security Scanner When asked to check, audit, or scan a skill for security, use SkillGuard. Commands Scan a local skill directory Scan with compact output (for chat) Check text for prompt injection Batch scan multiple skills Scan a ClawHub skill by slug Score Interpretation 80-100 ✅ LOW risk — safe to install 50-79 ⚠️ MEDIUM — review findings before installing 20-49 🟠 HIGH — significant security concerns 0-19 🔴 CRITICAL — do NOT install without manual review Output Formats Default: full text report --compact: chat-friendly summary --json: machine-readable full report --quiet: score and verdict only
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sundial-org/skillguard