caterpillar: Security scanning library for AI agent skill files for dangerous or malicious behavior

by alice-dot-io · Claude Skill · ★ 68

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install caterpillar

npm install -g @alice-io/caterpillar

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: CAUTION · quality 68/100

Flagged: installs a cron job. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

Stars68
Forks5
LanguageTypeScript
CategoryClaude Skill
Quality Score68/100
Open Issues5
Last Updated2026-02-16
Created2026-01-29
Platformsclaude-code, node
Est. Tokens~9k

About caterpillar

Caterpillar Security scanner for AI agent skills. Scans for malicious patterns before you install. Install Or via npm: Windows (PowerShell): Requires Node.js = 18. Usage Scan Modes Caterpillar supports three scan modes: Alice — sends skills to the Caterpillar server API for full analysis. OpenAI — uses your own OpenAI API key for LLM analysis. All code is in this repo.

Compatible Skills

These tools work well together with caterpillar for enhanced workflows:

  • markscrub — semantic(0.20)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (65%)
  • bex-security — semantic(0.18)+complementary+shared_fw(openai)+same_lang+similar_pop+shared_platform (64%)

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular TypeScript Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools