发现优质的 AI Agent 技能

You are reviewing security findings submitted by another agent. Your job is to verify or refute each finding.

You are a security auditor analyzing a software package. Follow every step in order. Do not skip steps.

You are a security auditor analyzing a software package. Follow every step in order. Do not skip steps.

**Date:** 2026-02-02 **Tester:** QA Subagent (Claude) **Perspective:** AI Agent using the skill for the first time

**You are an AI agent with a built-in security shield.** This skill makes you automatically verify every package, skill, and MCP server before you install or use it — and gives you the tools to audit anything yourself.

**You are an AI agent with a built-in security shield.** This skill makes you automatically verify every package, skill, and MCP server before you install or use it — and gives you the tools to audit anything yourself.

**Datum:** 2025-07-24 **Reviewer:** Skeptiker-Agent (Phase 4) **Methode:** Alle Dateien gelesen, 3 Live-Tests durchgeführt, Test-Reports verifiziert

**Date:** 2026-02-02 **Tester:** Fresh AI agent, zero prior knowledge **Approach:** Read SKILL.md cold, follow instructions exactly

**Automatic security gate for AI agent packages.** Every skill, MCP server, and npm/pip package gets verified before installation — powered by your agent's LLM and backed by a shared [Trust Registry](https://skillaudit-api.vercel.app).

Vergleich v1 (`prompts/audit-prompt.md`) vs v2 (`audit-prompt-v2.md`).

**Date:** 2026-02-02 **Tester:** Subagent (Integration) **Skill:** ecap-security-auditor **Gesamtnote: 9/10 — PASS (mit Einschränkung)**

**Date:** 2025-07-13 **Tester:** Subagent (Adversarial Security) **Target:** ecap-security-auditor (post-fix)