Agent 安全工作台
先扫描再信任，然后练习：审查 agent skill 的扫描器、打磨判断力的 CTF 训练，以及面向授权红队工作的测试库。
7 个技能
这张工作台有两个台面，第一个是审查：agent skill 是带着你的凭据运行的指令文件和脚本。nvidia/skillspector 在你安装之前检测 skill 中的漏洞、恶意模式、提示注入、数据外传和供应链风险。cisco-ai-defense/skill-scanner 干的就是名字承诺的事——给 agent skill 做安全扫描。prompt-security/clawsec 守护 OpenClaw 系 agent 这一侧，提供漂移检测、实时安全建议、自动化审计和 skill 完整性验证。
第二个台面是练习，仅限授权工作。ljagiello/ctf-skills 在 Web 渗透、二进制 Pwn、密码学、逆向工程、取证和 OSINT 各方向打磨基本功。gadievron/raptor 把 Claude Code 变成攻防两用、带编排安全工具链的安全 agent。snailsploit/claude-red 和 elementalsouls/claude-osint 是面向特定攻击面与外部侦察的结构化 skill 库——后者明确面向获授权的红队与漏洞赏金工作。
推荐顺序：装任何东西之前先扫描，让 clawsec 持续看护你自己的 agent 环境，练习类库只带上授权目标——CTF 靶场和范围内的安全委托。
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
15,946Sep 1, 2026Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
Star: 15,946
最近更新: Sep 1, 2026
Security Scanner for Agent Skills
Star: 2,493
最近更新: Sep 3, 2026
A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.
1,097Sep 4, 2026A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.
Star: 1,097
最近更新: Sep 4, 2026
Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more
3,168Aug 25, 2026Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more
Star: 3,168
最近更新: Aug 25, 2026
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.
3,707Sep 1, 2026Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.
Star: 3,707
最近更新: Sep 1, 2026
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.
3,024Aug 30, 2026claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.
Star: 3,024
最近更新: Aug 30, 2026
8 Claude skills · 100+ recon capabilities · 80 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · ~10,000 lines of structured tradecraft. Drop-in SKILL.md files that turn Claude into a god-mode external recon operator for authorized red-team and bug-bounty engagements.
2,531Aug 30, 20268 Claude skills · 100+ recon capabilities · 80 secret-regex patterns · 80+ dorks · 9 read-only credential validators · 27 attack-path templates · ~10,000 lines of structured tradecraft. Drop-in SKILL.md files that turn Claude into a god-mode external recon operator for authorized red-team and bug-bounty engagements.
Star: 2,531
最近更新: Aug 30, 2026