Security plugins

OWASP cdxgen toolkit for coding agents: generate, enrich, audit, sign, validate, convert, and explore CycloneDX BOMs (SBOM, CBOM, HBOM, OBOM, SaaSBOM, AI-BOM, VDR) across source code, containers, live hosts, and hardware.

14 skills · 1 agent · hooks

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns

hooks

Deterministic guardrails as PreToolUse hooks: blocks dangerous commands (force push, rm -rf, DROP TABLE), secret leaks, edits to protected files, and writes to build artifacts.

hooks

OWASP-style review: injection, auth, data exposure, weak crypto. Severity-ranked with file:line + fix.

BloodHound, AzureHound, GitHound/JamfHound/OktaHound OpenGraph attack-path query workflows, SCIM bridge references, and optional BloodHound MCP packaging.

9 skills

Social engineering research and phishing pretext workflows.

6 skills

Reusable Electron payload packaging, persistence, audit, and discovery workflows.

4 skills

Secrets firewall for tool calls: denies (or asks, per level) any Read/Edit/Write/Bash/Grep that would read, search, modify, or exfiltrate .env files, SSH keys, cloud credentials, or keystores, with tiered safety levels tunable via HOOK_SAFETY_LEVEL.

hooks

Prompt-injection tripwire for CLAUDE.md and .claude/rules files: flags invisible-Unicode smuggling, secret read/exfil directives, curl|sh, decode-and-execute, and hook/settings tampering as instructions load, then locks the session (every prompt and tool call denied) until a human clears it.

hooks

All seven guard hooks in one Node process: subagent-spawn-cap, config-guard, block-dangerous-commands, protect-secrets, protect-tests, git-safety, and case-insensitive-guard, first blocking verdict wins. One ~35 ms Node startup per tool call instead of seven. Do not install alongside the individual guard plugins.

hooks

Decompile Android APK/JAR/AAR with jadx, trace call flows through libraries, and document extracted APIs.

1 skill · 1 command

Hold irreversible Claude tool calls until a named human approves on their own device; mint an offline-verifiable Trust Receipt. Fail-closed.

1 MCP server · hooks

Detect malicious, vulnerable, or typosquatted npm packages from a conversation via npmscan.com's free, read-only MCP server.

5 skills · 1 MCP server

Five defensive security skills covering OWASP Top 10, supply-chain hardening, and secret scanning: pre-deployment audit checklists, secure authentication (hashing, sessions, JWT, OAuth, passkeys), API hardening (rate limiting, CORS, throttling), npm/bun install-time cooldown with a sandboxed bypass scan, and local Gitleaks scans for private repositories.

5 skills · 1 command

Security review and secure-coding skill covering OWASP Top 10:2025, ASVS 5.0, the OWASP LLM Top 10 (2026), and the OWASP Agentic Top 10 (2026).

1 skill

Security scanning, auditing, and compliance validation with 4 specialized agents, plus fail-closed hooks: PII/secrets guard, HMAC-chained tamper-evident audit (CloudWatch dual-write), token-budget circuit breaker

2 commands · 4 agents

Security vulnerability assessment (EN/KO). CII infrastructure (560+), AI Security, Robot Security (IEC 62443), Space Security (satellite/GSaaS/supply chain, CMMC/NIS2), Secure Coding (JS/Python/Pseudo Code, 46 CWE). Use /kesekit-start, /kesekit-start-ko, /kesekit-check, /kesekit-fix, /kesekit-guide etc.

9 skills

Agent Detection & Response (ADR) for Claude Code — guards commands, files, and web requests

1 skill · 1 MCP server · hooks

Runtime security enforcement for AI coding agents — policy hooks, audit receipts, threat hunting, and 15 MCP security tools.

3 skills · 6 commands · 1 agent · 1 MCP server · hooks

Mod (function hooks): masks secret values in tool results before the model reads them. Requires Claude Code 2.1.266+. On 2.1.266 to 2.1.286 set CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1; on 2.1.287+ Mods are public.

Investigate Chrome evidence with the ForensiX CLI: completeness first, cited records, Candidates as guesses

1 skill

Implements CSRF protection using synchronizer tokens, double-submit cookies, and SameSite attributes. Use when securing web forms, protecting state-changing endpoints, or implementing defense-in-depth authentication.

1 skill

OSS-only security for OWASP Top 10, pentest, vuln testing (XSS, SSRF, CSRF, business-logic, Host header), threat modeling (STRIDE, ATT&CK), Sigma rules, SAST, code audit, AI/LLM red-team, or replacing paid tools (Burp, Nessus, Splunk) with OSS.

1 skill

Validate at every layer data passes through to make bugs impossible. Use when invalid data causes failures deep in execution, requiring validation at multiple system layers.

1 skill

Checks each Claude Code tool call before it runs. Blocks a command that would send one of your keys out, and asks before the agent runs a package or script it copied from something it just read. Runs on your machine. No telemetry.

hooks

Firmware extraction, static analysis, Ghidra reverse engineering, emulation, and security reporting skills.

5 skills

🪼 Your security copilot as you build, your Blue Team when you audit, whether you're a developer or not.

9 skills · 1 MCP server

Offline security scanner for AI-agent repos, skills, plugins, and MCP servers. 29 scanners detect prompt injection, MCP tool poisoning, credential exposure, malicious lifecycle hooks, package IOCs, CVEs, CISA KEV exposure, and post-incident traces. Zero dependencies. Zero telemetry.

2 skills · hooks

Attacker tradecraft with the judgment, not just the commands. 40 offensive security skills for red teams and pentesters: web/API/auth exploitation (JWT, OAuth/OIDC, SAML, XXE, SSRF, deserialization, GraphQL, gRPC), Active Directory and Entra ID, AD CS ESC1-16, Kerberos delegation, Linux/Windows privilege escalation, cloud, managed Kubernetes, serverless, CI/CD, containers, mobile, wireless, Bluetooth/NFC, ICS/OT, Web3, reconnaissance, social engineering, persistence, and password cracking — plus deception-spotting and multi-day engagement discipline. Every skill fact-checked against primary sources. Pairs with secskills-core.

40 skills

The reverse-engineering and code-audit foundation both sides share. 30 dual-use security skills: native and Go/Rust/.NET/iOS/firmware reverse engineering, packers, and Flutter/React Native/Unity/Xamarin runtimes; source-code auditing with PHP-specific depth; webshell and backdoor hunting; multi-agent vulnerability-research orchestration; supply-chain, cryptography, MCP, and pull-request review; vetting third-party agent skills and MCP servers; AI/LLM security; ATT&CK technique mapping; engagement-state discipline; and findings reporting. Ships the ttp-index.json ATT&CK map. Every skill fact-checked against primary sources.

30 skills