Security

felipeinf/skillRx

Plugin Claude Code

Bundles 1 command · 11 tokens together

Security scanner for AI agent skills and plugins (Claude Code, Codex, Cursor, and 40+ more).

MuddySheep/vibeguard-local

Skill Claude CodeCodex

MANDATORY pre-flight for ALL SQL operations. Fire this skill IMMEDIATELY whenever the conversation involves SQL of any kind — writing it, proposing it, executing it, reviewing it, or even talking about it concretely. Triggers include any of these keywords appearing in user input or your own draft output…

KernelLord/pickysteve

Plugin Claude Code

Bundles 1 MCP server

Skill router and context picker for coding agents — picks the right skill per prompt, scans both the request and every retrieved doc for prompt injection.

paultyng/skill-issue

Skill Claude CodeCodex

Use when the user asks for a deep review, full review, comprehensive review, production readiness assessment, full audit, multi-domain audit, "security and reliability and code review", or "review everything". Also use when the user explicitly requests performance review alongside the comprehensive request (e.g.…

dinosn/security-knowledge-base

Skill Codex

Read, search, and inspect evidence in a Security Knowledge Base v1 repository, then validate or stage evidence-cited, revision-bound claim and finding proposals. Use when a task refers to a repository containing kb.json and the kb CLI, asks to check or update the security KB, or supplies an skb.context-packet/v1. Stop…

omermaksutii/RugProof

Plugin Claude Code

Bundles 35 commands, 23 agents · 1,912 tokens together

Smart contract security auditor for Claude Code. Rugproof your code before someone else does.

tashian/tsm

Plugin Claude Code

Bundles 1 skill · 37 tokens together

Touch-ID-gated secrets for AI coding agents. Provides safe credential injection for tools and MCP servers.

cylestio/agent-inspector

Cursor rule Cursor

Agent Inspector - AI Agent Security Analysis (scan, correlate static ↔ dynamic).

DollhouseMCP/collection

Agent Claude Code

Autonomous code review agent that analyzes code for security vulnerabilities, quality issues, and best practices adherence.

singhharsh1708/kitbash

Skill Claude CodeCodex

Review the current diff against this team's conventions and invariants before it ships. Invoke with /prereview before opening a PR, or run as a pre-push gate.

crunchtools/mcp-trentina

MCP server Claude CodeCodexCursor +2

Secure MCP gateway and quarantine for AI agent traffic — three-layer defense against prompt injection. Runs locally from the mcp-trentina-crunchtools Python package.

vulnmaster/CASE-UCO-SDK

Cursor rule Cursor

CASE/UCO SDK usage patterns for building digital forensics investigation graphs.

xfstudio/skills

Skill Claude CodeCodex

Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities.

1ikeadragon/awesome-offsec-claude

Skill Claude CodeCodex

Elite AI/LLM exploitation specialist - prompt injection, jailbreaking, agent exploitation, RAG poisoning, multi-modal attacks, model extraction, and system prompt leakage for CTF and red team engagements.

slartz/agent-security-awareness-training

Skill Claude CodeCodex

Mandatory security awareness onboarding for AI agents. Run this skill at the start of EVERY agent session, before performing any task — especially tasks involving tools, credentials, external content, email, file systems, cloud resources, or production systems. Also run it whenever the security policy file changes…

tr4m0ryp/shor

Skill Claude CodeCodex

Broken Access Control is OWASP #1, but there is no drop-in CLI (Autorize / AuthMatrix are Burp extensions). This is the procedure that carries the whole category: an authorization-matrix + A/B session-replay method driving curl, the playwright skill (per-identity sessions), and ffuf (ID enumeration). Live →…

bob-reis/claude-pentest-skills

Skill Claude CodeCodex

Network reconnaissance and port scanning using Naabu, hping3, and complementary tools.

ArianHobson333/claude-bug-bounty-stack

Skill Claude CodeCodex

Curated index of external hacking resources — meta-lists, frameworks, wordlists, payload banks, recon/OSINT, network, exploitation, and CTF tooling. Load when the user asks "what's the tool for X", "where do I find payloads for Y", "is there a wordlist for Z", or when planning which external resource to pull for a…

CaseyLabs/kc-secure-repo-template

Skill Claude CodeCodex

Use when changing or reviewing the Terraform-backed GitHub repository hardening workspace under config/infra, including provider pins, rulesets, default branch protection, required checks, secret scanning, Dependabot security updates, token handling, plan/apply behavior, and infra documentation. Do not use for…

edimuj/vexscan

Skill Claude CodeCodex

Scans extensions, skills, and code for security threats: prompt injection, malicious code, obfuscation, data exfiltration. Also scans inbound messages for injection patterns automatically.

jayelbotvibe-web/hermes-pentest-lab

Skill Claude CodeCodex needs its repo

Pentest finding interpretation encyclopedia — maps tool output to finding severity, CVSS scoring rules, and report-ready language. Answers 'What severity is this? What's the CVSS? How do I write this up?'.

Friz-zy/ai-capability-registry

Agent Claude Code

Never place secrets, credentials, tokens, PII, or production data in any field; reference affected files by redacted path only.

AI45Lab/SentrySkills

Skill Claude CodeCodex

Establish security boundaries before execution. Trigger this skill whenever involving command execution, file writing, sensitive data reading, external tool result adoption, or potential unauthorized requests; first output risk assessment and allowed/forbidden action lists.

harish-garg/security-scanner-plugin

Plugin Claude Code

Bundles 4 commands · 36 tokens together

Claude Code Plugin for scanning your code on your machine for vulnerabilities using GitHub's official data.