Security plugins

Agentic malware analysis across triage, dynamic analysis, specialized file analysis, detection engineering, and reporting.

6 skills

Reverse engineer Cocos Creator 2.x / 3.x games: recover scripts, scenes, prefabs, textures, audio, Spine/DragonBones; decrypt XXTEA-encrypted .jsc files; rebuild an editable project.

1 skill · 2 commands

STRIDE analysis, attack trees, trust boundaries, risk scoring. Grounded in NIST, MITRE ATT&CK.

9 skills · 4 commands

Secure coding review, OWASP Top 10, authentication/authorization design, cryptography.

9 skills · 3 commands

SAST, DAST, dependency scanning, penetration test scoping, API security review.

8 skills · 3 commands

Intent-based security enforcement for Claude Code: declared plans, policy rules, intent-drift blocking, CSRG cryptographic proofs, and audit logging. Production-hardcoded URLs (api.armoriq.ai + iap.armoriq.ai).

1 command · 1 MCP server · hooks

Intent-based security enforcement for Claude Code — dev variant. Staging/local toggleable via ARMORIQ_ENV (development → 127.0.0.1; default → staging-api.armoriq.ai). Tracks the dev branch HEAD; install only if you're contributing to armorClaude or running a local stack.

1 command · 1 MCP server · hooks

Scan plugins and skills for security risks (multi-agent support)

1 skill

macOS security hardening for Claude Code — PreToolUse/PostToolUse hooks that block secret exfiltration, prompt injection, persistence, and self-tampering.

hooks

Security response checks — php2shell-check: read-only exposure check and fix plan for the October 2026 PHP emergency patch (CVE-2026-109618, CVE-2026-109619)

1 skill

Security auditing pipeline — OWASP checks, vulnerability scanning, threat detection, cyber-defense multi-agent pipeline, and 13 protective hooks

7 skills · 2 agents · hooks

Connect Claude to your Windows PC's AppControl monitor — query running processes, tracked binaries, resource usage history, security events, and idle/uptime intervals.

1 MCP server

Tool-specific security scanning and runtime protection skills: Trivy, OWASP ZAP, SonarQube, Prisma Cloud, Fortify, Sysdig Secure, Sealed Secrets, and External Secrets Operator.

15 skills

AI Guard and AI-EDR security controls for coding agents, powered by Trajectory

1 skill · 4 commands · 1 MCP server · hooks

An offensive-security pipeline: map a codebase with Graft, hunt vulnerabilities with a per-class knowledge base, chain findings for escalation, verify real impact, and report (README/JSON/SARIF/doc/PDF).

18 skills · 5 agents

Analyze Linux kernel vulnerabilities from KASAN/UBSAN/BUG crash logs or CVE descriptions. Full root cause analysis, exploitability assessment, patch development, and QEMU verification.

1 skill

Pairs with a separately-installed local Little Canary service to screen submitted prompts. Advisory mode flags suspicious input; block mode stops turns the service rejects.

hooks

ODIN workflows for security review, vulnerability triage, and defensive implementation.

31 skills

ODIN workflows for fuzz harnesses, fuzzer setup, sanitizers, and coverage analysis.

11 skills

Skeptical-reading and prompt-injection defense for AI coding agents. Trust nothing. Ship safely.

2 skills · 1 agent

Ed25519 cryptographic signing for every Claude Code tool call. Hash-chained audit log, automatic key management, tamper-evident verification.

1 skill · hooks

渗透测试实战工作流 skill for Claude Code - 5阶段方法论/19类攻击playbook/2887份H1真实案例/国产组件指纹库

1 skill

Reverse engineering skill for Claude Code and other AI coding agents.

1 skill

Masks secrets and personal data in the tool results Claude Code reads, before the model sees them; reports what was in your prompts; and, with `shim watch`, shows what a session sent and what it cost. Runs locally with no account, network destination or telemetry.

Security tools: Code auditing, vulnerability scanning, compliance checks

Skills covering threat intel triage, IOC enrichment, MITRE ATT&CK mapping, phishing analysis, report writing, and dark web monitoring workflows.

5 skills

Scan Solana/Anchor code against the SOL-0XX rules as you work: MCP scan tool, full 52-rule guidance, /scan command.

1 command · 1 MCP server

Scan MCP servers, agents and packages for CVEs, supply-chain risk and exposed credentials; check a server before you add it; plan fixes.

9 skills · 2 MCP servers

Real-time pre-execution secret and exfiltration guard for Claude Code (audit mode), with the skarn-audit skill and a local read-only MCP server (four tools, no network call, every matched value masked).

1 skill · 1 MCP server · hooks

Real-time pre-execution secret and exfiltration guard for Codex CLI (audit mode), with the skarn-audit skill and a local read-only MCP server (four tools, no network call, every matched value masked).

1 skill · 1 MCP server · hooks