⚡

AI Skill Store

AI Agent Skill Marketplace
← Back to Skills

agent-redteam-kit

v1.0.0 approved updated today
USK v3 ✅ Verified
⬇ Download
Install Guide↓
🤖 Agent install commands (curl / MCP / Claude Desktop)
▸ curl one-liner
curl -L -o agent-redteam-kit.skill   "https://aiskillstore.io/v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=ClaudeCode"
▸ MCP tool call (after registering Skill Store MCP)
{
  "tool": "download_skill",
  "arguments": {
    "skill_id": "13867afc-4360-43f1-8758-0156e7e2dd59",
    "platform": "ClaudeCode"
  }
}
▸ Claude Desktop / Cursor MCP config (one-time)
{
  "mcpServers": {
    "skill-store": {
      "url": "https://aiskillstore.io/mcp/"
    }
  }
}
📖 Full agent API guide: /llms.txt  ·  MCP server card

当用户说『测一下这个AI安不安全』『会不会被越狱』『让AI干危险的事它听不听』『上线前做对抗测试』，或要给一个 agent/提示词做安全性红队时使用。中英双库扫描越狱/危险能力请求（DAN/忽略指令/提权/数据外泄/自改进等），给出风险分级+加固建议，并设「危险操作闸门」（有门禁）。可运行脚本（redteam_scan 扫描器）。理论根基：LGD 三律之有门禁（危险动作先过闸）。触发词：红队、red team、越狱、jailbreak、对抗测试、prompt攻击、AI安全测试、危险指令、安全评估。

# 红队 # red team # 越狱 # jailbreak # 对抗测试 # AI安全 # 有门禁

Basic Info

Owner 👤 Steven Zhao Category — Registered 2026-10-16 Last Updated 2026-10-16 Latest Version 1.0.0 Packaged At 2026-10-16 Vetting Status approved Downloads 0 Checksum (SHA256) 822750c3d0e3509eefbfc77854712dc6b7ce1880e824874a6b1c4fba72961de9

⚡ AGENT INFO USK v3

Capabilities
red_team_scan jailbreak_detection dangerous_action_gate risk_tiering security_assessment
Permissions
✗ network
✗ filesystem
✗ subprocess
Interface
type: cli   entry_point: scripts/redteam_scan.py   runtime: python3   call_pattern: args
Agent API
# 스킬 스키마 조회 (에이전트가 호출 방법을 파악) GET /v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/schema # 플랫폼별 자동 변환 다운로드 GET /v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=OpenClaw GET /v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=ClaudeCode GET /v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=ClaudeCodeAgentSkill GET /v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=Cursor GET /v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=GeminiCLI GET /v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=CodexCLI GET /v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=CustomAgent

Installation

1
Install the skill using openclaw_skill_manager.py.
python openclaw_skill_manager.py --install agent-redteam-kit
2
Verify installation
python openclaw_skill_manager.py --list-installed
3
Install a specific version (optional)
python openclaw_skill_manager.py --install agent-redteam-kit --version 1.0.0
1
Download the skill package.
curl -O https://aiskillstore.io/v1/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download
2
Place it in the Claude Code commands directory.
unzip agent-redteam-kit.skill -d ~/.claude/commands/agent-redteam-kit/
3
Use it as a slash command in Claude Code.
/agent-redteam-kit
1
Download the Agent Skills package.
curl -O https://aiskillstore.io/v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=ClaudeCodeAgentSkill
2
Unzip it into the Claude Code skills directory.
unzip agent-redteam-kit-agent-skill-*.skill -d ~/.claude/skills/agent-redteam-kit/
3
Restart Claude Code — the skill is auto-loaded at session start. No slash command needed.
1
Download the Cursor-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=Cursor
2
Unzip and place it in a permanent location.
unzip agent-redteam-kit-cursor-*.skill -d ~/.cursor/skills/agent-redteam-kit/
3
Add the MCP server config to .cursor/mcp.json, then restart Cursor.
cat ~/.cursor/skills/agent-redteam-kit/cursor_mcp_config.json
1
Download the Gemini CLI-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=GeminiCLI
2
Unzip and place it in a permanent location.
unzip agent-redteam-kit-geminicli-*.skill -d ~/.gemini/skills/agent-redteam-kit/
3
Add the MCP server config to ~/.gemini/settings.json, then restart Gemini CLI.
cat ~/.gemini/skills/agent-redteam-kit/gemini_settings_snippet.json
1
Download the Codex CLI-converted package.
curl -O https://aiskillstore.io/v1/agent/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download?platform=CodexCLI
2
Unzip and place it in a permanent location.
unzip agent-redteam-kit-codexcli-*.skill -d ~/.codex/skills/agent-redteam-kit/
3
Add the MCP server config to ~/.codex/config.toml, then restart Codex CLI.
cat ~/.codex/skills/agent-redteam-kit/codex_config_snippet.toml
1
Download the skill package via REST API.
GET https://aiskillstore.io/v1/skills/13867afc-4360-43f1-8758-0156e7e2dd59/download
2
Place it in your agent platform's skills directory.
cp agent-redteam-kit.skill ./skills/
3
Fetch platform-specific details via the Install Guide API.
GET https://aiskillstore.io/v1/skills/13867afc-4360-43f1-8758-0156e7e2dd59/install-guide?platform=CustomAgent

Requirements

Security Vetting Report

Vetting Result CAUTION

Findings: ["메타데이터 경고: 권장 필드 없음: 'platform_compatibility' (SKILL.md v2 권장)", 'USK v3 경고: 이 스킬은 자동 변환 조건을 충족하지 않아 manual_install로 처리됩니다']

✅ No security risks found.

AI Review Stage

Reviewer gemini Risk Level 🟢 Low Review Summary AI 에이전트의 보안 취약점(탈옥, 위험 명령 등)을 탐지하는 스킬로, 악의적인 코드나 무단 데이터 접근 없이 안전하게 구현되었습니다.

Issues Found

  • AI 응답이 토큰 한도로 잘렸으나 verdict 추출 성공
Reasoning

{ "verdict": "approved", "risk_level": "low", "summary": "AI 에이전트의 보안 취약점(탈옥, 위험 명령 등)을 탐지하는 스킬로, 악의적인 코드나 무단 데이터 접근 없이 안전하게 구현되었습니다.", "issues": [], "reasoning": "제공된 스킬 메타데이터와 코드 파일을 분석한 결과, 다음과 같은 판단을 내렸습니다.\n\n1. **선언된 permissions과 실제 코드 일치 여부:**\n * `network: false`: 코드에서 네트워크 통신을 시도하는 부분이 없습니다. 일치합니다.\n * `subprocess: false`: 코드에서 외부 프로세스를 실행하는 부분이 없습니다. 일치합니다.\n * `filesystem: false`: 메타데이터에는 파일 시스템 접근이 `false`로 선언되어 있으나, `allowed-tools`에 `Read`가 명시되어 있고 `input_s

Version History

Version USK v3 Vetting Status Packaged At Downloads Changelog
v1.0.0 ✓ approved 2026-10-16 ⬇ 0 1.0.0: initial upload (USK v3)

Reviews & Ratings

No reviews yet. Be the first to leave one!

✍️ Write a Review