Security

atlassian/forge-skills

Cursor rule Cursor ✓ vendor

Detect missing authorization checks in Forge resolvers for sensitive operations.

aidongise-cell/prism-scanner

Skill Claude Code

Security scanner for AI Agent skills, plugins, and MCP servers. Use when: user asks to scan a skill, check if a plugin is safe, vet an MCP server, review skill security, detect malicious code, supply chain safety, or says 'is this safe to install', 'scan this skill', 'check this MCP server', 'security scan'…

cdmx-in/security-review

Plugin Claude Code

Bundles 1 skill · 106 tokens together

Runs real security scanners over code, full git history, dependencies, IaC and Supabase/Firebase row-level security, then verifies every finding against source before reporting.

Raftersecurity/rafter-cli

Skill Claude CodeCodex

REQUIRED before writing code for any feature touching auth, payments, credentials, tokens, sessions, file upload, user data, untrusted input, deserialization, network endpoints, or data deletion. Scope by that surface, not the task label — a research/experimental/local-only feature with none of it doesn't need this.…

lhuciverjobs-ui/fox

Skill Claude CodeCodex

Business logic vulnerability playbook. Use when reasoning about workflows, race conditions, price manipulation, coupon abuse, state machines, and multi-step authorization gaps.

Promastergame/tinyapk-lab

Skill Claude CodeCodex

Run R8/ProGuard on Android APK without Gradle — shrink, obfuscate and minify DEX using R8 that's already inside d8.jar.

AuroraProudmoore/java-audit-skill

Skill Claude CodeCodex

A code-security auditing method for Java, Kotlin, JavaScript, and TypeScript projects, including Spring, React, Vue, and related frameworks. It scans code for common security weaknesses and produces audit findings.

JamalMohafil/claude-skills

Skill Claude CodeCodex

Run a security review of code changes exactly like Claude Code's /security-review command — but in ANY AI coding agent (Claude Code, Cursor, Codex, Windsurf, Gemini CLI, Cline…). Reviews the pending branch diff (or a specific PR, uncommitted changes, or a whole file/folder) for HIGH-CONFIDENCE, actually-exploitable…

2233admin/reverse-skill-evolver

Skill Claude CodeCodex

Goal-contract, capability graph, TraceCard, and promotion-gate control plane for self-evolving reverse/security skill routing. Use before macro-routing when the task needs end-to-end completion, route repair, or reusable learning.

codebygarv/Ai-skills

Skill Claude CodeCodex

Reviews how a feature or system handles PII, data retention, and consent against common privacy-framework principles (GDPR-style). Use when a feature collects, stores, or processes personal data - not a substitute for legal advice.

habedi/omni-lpr

MCP server Claude CodeCodexCursor +2

An MCP server for automatic license plate recognition. Remote server at {baseurl}.

wrxck/auto-audit

Plugin Claude Code

Bundles 9 skills, 4 agents, 1 hook · 820 tokens together

Autonomous security auditor. Scans a GitHub repo for vulnerabilities, triages false positives, writes a PoC, fixes each confirmed bug in its own PR, independently reviews the fix, and merges when the review is clean.

x-cmd/skill

Skill Claude Code

Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.

santosomar/ethical-hacking-agent-skills

Skill Claude Code

Creates Nuclei YAML templates for vulnerability detection across HTTP, DNS, TCP, SSL, and other protocols. Use when converting a confirmed vulnerability, misconfiguration, or exposure into a reusable automated check — for example, turning a manual finding into a detection rule, writing a CVE check, or codifying a…

operantlabs/operant-mcp

MCP server Claude CodeCodexCursor +2

Security testing MCP server for penetration testing, forensics, and vulnerability assessment. Runs locally from the operant-mcp npm package.

ZealynxSecurity/krait

Plugin Claude Code

Bundles 3 skills · 146 tokens together

Smart contract security analysis powered by 4,500+ real audit findings from Solodit. Quick scans, full framework assessments, and integration with audit-readiness.zealynx.io.

kroegha/kali-docker-pentesting

Skill Claude CodeCodex

Comprehensive pentesting toolkit using Kali Linux Docker container. Provides direct access to 200+ security tools without MCP overhead. Use when conducting security assessments, penetration testing, vulnerability scanning, or security research. Works via direct docker exec commands for maximum efficiency.

Stanislav-Povolotsky/jddlab

Skill Claude CodeCodex

Detect and reverse Java/Android obfuscation with jddlab - ProGuard/R8 renaming, string encryption, control-flow flattening and commercial protectors, using java-deobfuscator, simplify and dex2jar. Use when decompiled code is obfuscated or strings are encrypted.

MaxwellCalkin/sentinel-ai

Plugin Claude Code

Bundles 1 skill, 5 commands, 1 MCP server · 52 tokens together

Real-time safety scanning for LLM interactions. Detects prompt injection, PII leaks, harmful content, toxicity, obfuscation, secrets, and dangerous tool calls — 600-case benchmark at 100% accuracy with sub-millisecond latency.

ShulkwiSEC/bb-huge

Skill Claude CodeCodex needs its repo

Bug bounty findings secretary, tracker, and workspace initializer for the bb-huge portal. Use this skill for web security research, vulnerability hunting, and hunt workspace setup. Triggers on: "log finding", "save finding", "add to bb-huge", "record vulnerability", "update finding", "show findings", "bb-huge stats"…

miles990/claude-software-skills

Skill Claude Code

Enterprise-grade repository analysis with arc42/C4 architecture documentation, technical debt quantification, security assessment, and multi-stakeholder reporting.

mikrotik-mcp/mikrotik-mcp

MCP server Claude CodeCodexCursor +2

MCP server for MikroTik RouterOS — 780+ tools over SSH for firewall, NAT, routing, DHCP, DNS, WireGuard, wireless, QoS and more. Runs locally from the @usex/mikrotik-mcp npm package.

corv89/shannot

Skill Claude CodeCodex

Run diagnostic scripts in sandbox with human approval (MCP tool).

Delego-Dev/delego

MCP server Claude CodeCodexCursor +2

Intent-bound action authorization for AI agents — authorise before a credential is used, require human approval for sensitive actions, and prove every action traces back to the instruction that authorised it. Runs locally from the delego Python package. Needs 1 environment variable to run.