llm-pentest-checklist：把 LLM 渗透测试方法论装进 Agent Skills
llm-pentest-checklist 是 SkillHub 社区 it-ops-security 类 Skill（@user_3fd87291/llm-pentest-checklist，v1.0.1，无需 API Key）。包内含 SKILL.md 实战手册与 llm-pentest-checklist.md 九模块可勾选清单，覆盖攻击面测绘、提示注入、Agent/RAG/MCP、云原生与供应链测试思路，并映射 OWASP LLM Top 10、MITRE ATLAS 等框架。文章说明 skillhub 安装命令、Cursor/Codex 等 skills 目录及授权测试下的典型协作方式，并注明附录工具未随包分发。
Read MoreCybersecurity Skills 网络安全技能集：把渗透与评估能力装进 Agent Skill
Cybersecurity Skills 网络安全技能集是 SkillHub 社区 Skill（@user_922b1001/cybersecurity-skills-wrap，v1.0.0，it-ops-security），整合开源渗透与评估工具，基于 Kali 工具链提供统一 CLI 与自动化脚本，覆盖漏洞扫描、密码破解、网络侦察、权限维持等能力，面向安全工程师与 CTF 等场景。本文依据官方简介与 SkillHub 安装文档说明 skillhub CLI 安装、Cursor 等客户端 skills 目录配置及合规使用注意；不要求 API Key。
Read More攻击性业务逻辑 Skill：用状态机思路辅助业务逻辑漏洞测试
SkillHub 社区 Skill「攻击性业务逻辑」（@user_3c6cb52e/offensive-business-logic-sh-hxm687，v1.0.0）将赏金场景中常见的业务逻辑测试步骤写入 SKILL.md：多步流程状态机建模、转移条件审计、状态/身份/输入/频率多轴探测、缺陷串联与财务影响量化。无需 API Key。本文说明其定位、核心工作流，以及通过 skillhub install 安装到 Cursor、Claude Code、Codex 等 skills 目录的方式与典型提示用法，并强调仅在授权范围内测试。
Read More开放重定向 Skill：为 Agent 提供开放重定向攻防要点
SkillHub 社区 Skill「开放重定向」（@user_3c6cb52e/open-redirect-lr-dwn3，v1.0.0，it-ops-security）通过 SKILL.md 向 Agent 注入开放重定向专家 playbook：参数跳转、JS sink、过滤器绕过，以及与钓鱼、CSRF Referer、OAuth 窃密、SSRF 的链式组合。无需 API Key。本文说明其定位、已核实功能、skillhub 安装命令与各客户端 skills 目录，并给出可复现的对话式用法与授权测试注意事项。
Read Moreshannon渗透测试：用五阶段流程做 AI 驱动的白盒渗透测试
shannon渗透测试是 SkillHub 社区 Skill（@user_7188f9b6/shannon-pentest，v1.0.1，it-ops-security），基于 Shannon 改进，用 AI 驱动白盒渗透测试。流程覆盖前期侦察、侦察、漏洞分析、漏洞利用与报告生成，并强调结构化交付。适用于 Web 应用、API 与源代码的安全审计、渗透测试与漏洞验证；标签 requires_api_key=false。安装需按 skillhub.cn/install/skillhub.md 使用 skillhub install 并指定 Agent 的 skills 目录。
Read More网安技能：在 Agent 里串起安全学习路径与 SRC 实战问答
网安技能（@user_d2cc4baf/cybersec-learning）是 SkillHub 社区版 it-ops-security 类 Skill，v1.0.8，无需 API Key。融合学习模式（法律→基础→工具→靶场→攻防→就业）与实战模式（TSRC/ASRC/BSRC 等 SRC 掘金）。本文基于 SkillHub 官方简介与安装文档，说明定位、触发语、skillhub install 安装到 Cursor/Claude Code 等 skills 目录的方法及典型提问示例，并强调授权测试与合规边界。
Read MoreDeepSeek Harness Plugin Introduction: Stavros DSH Redteamer
`stavros-dsh-redteamer` is an authorized AI red teaming/pentesting plugin for DeepSeek Harness (DSH). Maintained by `CSI-entitymorton`, it centers on a persona named Stavros and includes 24 specialized sub-agents and 78 zero-dependency tools to assist with security testing. The plugin runs with the permissions of the current process and is intended solely for use in authorized environments. Users are responsible for reviewing the source code and ensuring compliance.
Read Moredsh-pentest-bugtrace: BugTraceAI Penetration Testing Mode Plugin
dsh-pentest-bugtrace is a penetration testing plugin designed for DeepSeek Harness (DSH), aimed at simplifying the process of building security testing agents. The plugin encapsulates BugTraceAI’s MCP tools and workflows into a standard plugin, with built-in penetration testing roles, authorization rules, and preset runbooks. Users only need to configure environment variables and run a specific command to activate the agent for authorized scanning, vulnerability validation, and report generation. It supports multiple MCP tools to drive the BugTraceAI engine and includes a fail-open policy to handle backend service unavailability, greatly reducing the configuration barrier for penetration testing agents.
Read MoreIntroduction to the DeepSeek Harness Plugin: dsh-redteam-model
`dsh-redteam-model` is a security research plugin for DeepSeek Harness (DSH), designed to address the issue that AI systems possess knowledge but lack workflow guidance. It provides 10 security modes (such as penetration testing and code auditing) and 17 runtime plugins, covering the full workflow of asset discovery, offensive and defensive evaluation, and more. It supports integration with scanning tools and the MCP tool platform. Users can deploy it with one click via the command line or a Web interface, making it suitable for authorized bug bounty and CTF scenarios. It emphasizes the critical role of workflow design in improving efficiency and maintaining control over objectives.
Read Moredsh-vulnsec-bridge: A security plugin for integrating VulnClaw and DeepSec into DeepSeek Harness
# Introduction When performing security-related tasks in DeepSeek Harness (dsh), the common practice is to open a separate terminal to run penetration testing or code auditing CLIs, then copy the output back to the session for further analysis. As tool capabilities are not registered as dsh tools, the model cannot invoke them directly, and their results cannot be integrated into subsequent automated workflows. dsh-vulnsec-bridge is a bridging plugin designed for this scenario: it wraps VulnClaw (AI penetration testing CLI) and DeepSec (Shield code auditing + Spear authorized penetration) into dsh plugins, providing 18 security tools and a graphical "Security Workbench" panel. Below, we introduce its features, installation methods, and typical usage. First, let's discuss the prerequisites: the plugin's penetration...
Read More