安全 类技能
Skill Atlas 收录的 安全 类 AI Agent 技能，共 14 个，含用途说明、安装命令与安全审计状态。
按分类浏览
安全 技能列表
- offensive-active-directoryActive Directory attack methodology for internal network red team engagements. Covers reconnaissance (BloodH…
- ctf-ai-mlProvides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adver…
- 007Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, inciden…
- offensive-netexecUse this skill whenever the user asks about NetExec (nxc) — a network exploitation and post-exploitation too…
- active-directory-attacksThis skill should be used when the user asks to "attack Active Directory", "exploit AD", "Kerberoasting", "D…
- ctf-cryptoProvides cryptography attack techniques for CTF challenges. Use when attacking encryption, hashing, signatur…
- idea-devils-advocate想法群聊室 — 反方角色。被 idea-team 主编排器调用，或用户单独说"反方意见"、"挑这个想法的刺"、"为什么会失败"、"找漏洞 / 反例"、"devil's advocate"时触发。**专门挑漏洞、找隐藏…
- provenance收集系统全链路操作日志，生成可追溯的执行证据链与向量索引，是多智能体系统可观测性与安全审计的底座。
- api-fuzzing-bug-bountyThis skill should be used when the user asks to "test API security", "fuzz APIs", "find IDOR vulnerabilities…
- ctf-forensicsProvides digital forensics and signal analysis techniques for CTF challenges. Use when analyzing disk images…
- offensive-api-securityComprehensive API security testing methodology covering REST, gRPC, and WebSocket attack surfaces. Addresses…
- ctf-malwareProvides malware analysis and network traffic techniques for CTF challenges. Use when analyzing obfuscated s…
- offensive-jwtJWT attack methodology for penetration testers. Covers algorithm confusion (alg:none, RS256→HS256), weak HMA…
- ctf-miscProvides miscellaneous CTF challenge techniques for problems that do not cleanly fit the main categories. Us…