by Jueze-2019
DSH RedTeam 模式:把 DeepSeek Harness 变成红队作战指挥台——一个靶标名称拉起信息收集/漏洞检测/漏洞利用/内网渗透四个角色,资产与战果实时落入本地 SQLite 事实库(仅供已授权测试)
# Add to your Claude Code skills
git clone https://github.com/Jueze-2019/dsh-redteam-modeGuides for using ai agents skills like dsh-redteam-mode.
Last scanned: 9/29/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-29T10:25:57.530Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how dsh-redteam-mode compares with popular alternatives.
dsh-redteam-mode is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by Jueze-2019. DSH RedTeam 模式:把 DeepSeek Harness 变成红队作战指挥台——一个靶标名称拉起信息收集/漏洞检测/漏洞利用/内网渗透四个角色,资产与战果实时落入本地 SQLite 事实库(仅供已授权测试). It has 71 GitHub stars.
Yes. dsh-redteam-mode passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/Jueze-2019/dsh-redteam-mode" and add it to your Claude Code skills directory (see the Installation section above).
dsh-redteam-mode is primarily written in JavaScript. It is open-source under Jueze-2019 on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh dsh-redteam-mode against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
把 DeepSeek Harness(DSH)变成一台红队作战指挥台: 只发一个靶标单位名称,主会话拉起一支执行智能体团队(信息收集 → 资产梳理 → 漏洞发现 → 漏洞利用 → 内网渗透), 所有发现实时落进本机 SQLite 事实库,并在界面右侧栏的常驻控制台里可视化。
⚠️ 仅限已获授权的攻防演练 / 渗透测试使用。 本仓库是智能体编排与事实库的工程实现, 不包含任何漏洞利用代码;使用者须自行确保对目标拥有书面授权。
53 个 redteam_* 工具 · 14 个随包技能(+9 个攻击链技能见工具箱附件) · 12 个控制台页签 · 22 张事实库表
dsh plugin --profile web add dsh-redteam-mode
装完重启一次 dsh web,在界面助手栏选预设 红队模式,直接发靶标单位名称即可开工。
首次启动会自动装好预设与 14 个随包技能,不需要手动拷文件。
环境准备(首次使用):
bash "$DSH_HOME/redteam/setup.sh" --check # 体检:缺什么一眼看清
bash "$DSH_HOME/redteam/setup.sh" # 装齐工具 + 引导填 FOFA_KEY / VPS
前置:DSH 能正常
dsh web启动;Node.js ≥ 22.13(依赖内置node:sqlite)。 请跑在专供演练的 Kali 虚拟机里,不要跑在日常办公机/宿主机上。
直接从 Release 安装某个版本(不依赖 npm,也不需要下载解压):
dsh plugin --profile web add \
https://github.com/Jueze-2019/dsh-redteam-mode/releases/download/v0.11.4/dsh-redteam-mode-0.11.4.tgz
# 装完重启一次 dsh web
下载 tarball 再装(适合离线机器,附件同在同一下载页):
curl -LO https://github.com/Jueze-2019/dsh-redteam-mode/releases/download/v0.11.4/dsh-redteam-mode-0.11.4.tgz
dsh plugin --profile web add ./dsh-redteam-mode-0.11.4.tgz
从源码装:
# 生成市场包 → 同步到 profile → 刷新预设/技能,一步到位(推荐)
node scripts/deploy-local.mjs
node scripts/deploy-local.mjs --restart # 顺带重启 dsh web(会中断当前会话)
PROFILE=~/.dsh/profiles/web
mkdir -p "$PROFILE/node_modules"
for p in redteam-store redteam-tools redteam-ui; do
ln -sfn "$PWD/packages/$p" "$PROFILE/node_modules/dsh-$p"
done
# 注意:DSH ≥0.1.7 起模式列表来自 cordis.patch.yml 生成区里的 preset-redteam 声明行,
# 不再是 $DSH_HOME/.agent-presets/ 目录 —— 手工部署必须把 cordis.patch.yml 一起同步过去。
细节见 docs/详细文档.md 第 7 章。
redteam_preflight 逐个技能体检,缺 key、缺 VPS、缺工具一次性说清,补不齐就说降级方案。$DSH_HOME/redteam/,无遥测、无上报、无云端同步。面板右上角常驻版本号 + 一键更新(检测到有智能体在跑会拦住)。
完整说明、53 个工具清单、开发与发版流程见 docs/详细文档.md。
面向授权范围内的安全评估:攻防演练、红蓝对抗、企业自检、教学研究。 未获授权的扫描、探测、入侵或数据获取均属违法,与本项目作者无关。MIT,见 LICENSE。