菜单
Expert security auditor for AI Skills and Bundles. Performs non-intrusive static analysis to identify malicious patterns, data leaks, system stability risks, and obfuscated payloads across Windows, macOS, Linux/Unix, and Mobile (Android/iOS).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
This skill should be used when the user asks to "attack Active Directory", "exploit AD", "Kerberoasting", "DCSync", "pass-the-hash", "BloodHound enumeration", "Golden Ticket", ...
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines,...
This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.
| name | audit-skills |
| description | Expert security auditor for AI Skills and Bundles. Performs non-intrusive static analysis to identify malicious patterns, data leaks, system stability risks, and obfuscated payloads across Windows, macOS, Linux/Unix, and Mobile (Android/iOS). |
| category | security |
| risk | safe |
| source | community |
| date_added | 2026-03-07 |
| author | MAIOStudio |
| tags | ["security","audit","skills","bundles","cross-platform"] |
| tools | ["claude","gemini","gpt","llama","mistral","etc"] |
Expert security auditor for AI Skills and Bundles. Performs non-intrusive static analysis to identify malicious patterns, data leaks, system stability risks, and obfuscated payloads across Windows, macOS, Linux/Unix, and Mobile (Android/iOS). 2-4 sentences is perfect.
Performs non-intrusive static analysis to identify malicious patterns, data leaks, system stability risks, and obfuscated payloads.
Analyzes code for platform-specific security issues across Windows, macOS, Linux/Unix, and Mobile (Android/iOS).
sudo, chown, chmod, TakeOwnership, icacls, Set-ExecutionPolicy.touch -t, setfile (macOS), attrib (Windows), Set-ItemProperty, chflags.chmod 000, chattr +i (immutable), attrib +r +s +h, Deny ACEs in icacls.%USERPROFILE%, /Users/, or /etc/..bat, .cmd, cmd.exe /c, vbs, cscript, wscript..sh, .bash, .zsh, chmod +x followed by execution..ps1, powershell -ExecutionPolicy Bypass -File ....-WindowStyle Hidden, -w hidden, -noprofile.msiexec /qn, choco uninstall, reg delete.apt-get purge, yum remove, rm -rf /usr/bin/....brew uninstall, deleting from /Applications.adb shell, pm install, am start, apktool, dex2jar, keytool.AndroidManifest.xml (permissions), classes.dex, or strings.xml.xcodebuild, codesign, security find-identity, fastlane, xcrun.Info.plist, Entitlements.plist, or Provisioning Profiles.curl, wget, Invoke-WebRequest, Invoke-RestMethod, scp, ftp, nc, socat..env, .ssh, cookies.sqlite, Keychains (macOS), Credentials (Windows), keystore (Android).Stop-Service, taskkill /f, sc.exe delete.kill -9, pkill, systemctl disable/stop, launchctl unload.dd), firmware/BIOS calls, kernel module management.Base64, Hex, XOR loops, atob().reg add (Run keys), schtasks, crontab, launchctl (macOS), systemd units.curl ... | bash, iwr ... | iex.CATALOG.md.adb shell or sudo?Generates a security report with a score (0-10), platform target identification, flagged actions, threat analysis, and mitigation recommendations.
"Perform a security audit on this skill bundle"
"Scan for mobile threats in this AI skill"
Problem: Executing code during audit Solution: Stick to static analysis methods only
Problem: Missing cross-platform threats Solution: Check for platform-specific security issues on all supported platforms
Problem: Failing to detect obfuscated payloads Solution: Look for encoding patterns like Base64, Hex, XOR loops, and atob()
@security-scanner - Additional security scanning capabilities