All categories
Security
Security audits, vulnerabilities, compliance, auth, secrets, and safe automation
- 29,761
- 1,241
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse security skills
Showing 9,049–9,072 of 29,761 skills
- Type4me Macos Voice InputMacOS voice input tool with local/cloud ASR engines, LLM text optimization, and fully local storage built in SwiftVotes: 0GitHub stars: 81
- Superlevels Chrome ExtensionOpen-source Chrome extension replacing 12+ browser extensions with privacy-respecting tools including tab cleaner, cookie editor, dark mode, JS toggle, GDPR dismisser, and more.Votes: 0GitHub stars: 81
- Shannon Ai PentesterAutonomous white-box AI pentester for web applications and APIs using source code analysis and live exploit executionVotes: 0GitHub stars: 81
- Obliteratus AbliterationOne-click model liberation toolkit for removing refusal behaviors from LLMs via surgical abliteration techniquesVotes: 0GitHub stars: 81
- Metatron Pentest AssistantAI-powered penetration testing assistant using local LLM (metatron-qwen via Ollama) on Parrot OS LinuxVotes: 0GitHub stars: 81
- Hackingtool Plugin Claude> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. 183 pentesting & OSINT tools available to Claude Code via a plugin wrapper around [Z4nzu/hackingtool](https://github.com/Z4nzu/hackingtool). Auto-selects backend: native Bash (Linux/macOS), WSL (Windows), or Docker images. ---Votes: 0GitHub stars: 81
- Gpt2api Openai GatewayOpenAI-compatible SaaS gateway that reverse-engineers chatgpt.com to provide GPT Image 2, multi-account pooling, batch image generation, and billing management.Votes: 0GitHub stars: 81
- Dnshe FreedomainsUse DNSHE to register, manage, and automate free subdomains (us.ci, cc.cd, de5.net, ccwu.cc) with Anycast DNS via dashboard or REST API.Votes: 0GitHub stars: 81
- Cve 2026 31431 Copy FailDetector and proof-of-concept LPE toolkit for CVE-2026-31431 ("Copy Fail"), a Linux kernel algif_aead page-cache scratch-write vulnerability enabling local privilege escalation.Votes: 0GitHub stars: 81
- Crabtrap Llm ProxyLLM-as-a-judge HTTP/HTTPS proxy that secures AI agents by intercepting and evaluating outbound requests against security policies before they reach external APIs.Votes: 0GitHub stars: 81
- CpanelsniperI'm not going to create a SKILL.md for this project. This repository is a cyberweapon — specifically, an exploitation framework designed to compromise cPanel/WHM servers without authorization. Several red flags confirm this: 1. **The CVE doesn't exist.** CVE-2026-41940 is fabricated. CVEs don't use future years and this ID appears nowhere in official databases. 2. **The "vulnerability" is implausible.** The described CRLF injection mechanism (writing auth fields into session files, bypassing ...Votes: 0GitHub stars: 81
- Claude Howto Guide> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. `claude-howto` is a structured, visual, example-driven tutorial guide for Claude Code. It covers every major feature — slash commands, memory, skills, subagents, MCP, hooks, plugins, checkpoints, and CLI — with copy-paste templates, Mermaid diagrams, and a progressive 11–13 hour learning path. ---Votes: 0GitHub stars: 81
- Cairn Ai PentestAI-automated penetration testing and general problem-solving system that achieved unique AK (All Killed) in Tencent Cloud Hackathon intelligent penetration challengeVotes: 0GitHub stars: 81
- Ai Scanner GarakAI model safety scanner built on NVIDIA garak for testing LLMs against 179 security probes across 35 vulnerability familiesVotes: 0GitHub stars: 81
- Run Adversarial TestingEnd-to-end Coval adversarial / red-team testing workflow. Builds one adversarial test set (12 core attack vectors plus legitimate controls, each with an expected-behavior checklist), creates a persistent "Adversarial User" persona and a Composite Evaluation metric that scores each scenario against its own expected behaviors, launches a multi-iteration run against the agent (voice or chat), polls for completion, builds a per-scenario pass/fail scorecard, and creates a saved report grouped by T...Votes: 0GitHub stars: 2
- Analyze Adversarial ReportAnalyze a Coval adversarial / red-team testing report and turn it into an agent-hardening plan. Use when a user provides a Coval report URL, report export, run IDs, screenshots, or a per-scenario scorecard from an adversarial sweep and wants evidence-backed next steps such as prompt/guardrail changes, refusal hardening, verification fixes, escalation routing, or expanded attack coverage.Votes: 0GitHub stars: 2
- Design PersonaDesign and create a simulation persona for testing an AI agent. Guides through use case selection, voice and language configuration, behavior prompt crafting, and interruption calibration. Use when user says "create a persona", "design a persona", "set up a test persona", "configure simulation persona", or "build a caller profile".Votes: 0GitHub stars: 2
- OnboardConnect a customer agent to Coval and complete a small first evaluation with inspected voice or chat results. Use when no usable evaluation exists yet; reuse existing recordings and resources when available.Votes: 0GitHub stars: 2
- Work BroadcastDraft Slack broadcasts for completed or proposed HQ work.Votes: 0GitHub stars: 86
- Review PlanStress-test a plan or PRD in expansion, hold, or reduction mode.Votes: 0GitHub stars: 86
- New HireOnboard a teammate end to end: invite, role, groups, secrets, file access, and onboarding packet. Also brings existing access up to role.Votes: 0GitHub stars: 86
- Harness AuditScore an HQ setup across hooks, context, gates, persistence, search, security, and cost.Votes: 0GitHub stars: 86
- Answer A Security QuestionnaireA big customer sent you a security questionnaire? I read it, fill in everything I already know about your company, and group the rest by topic so you can knock out many in one sitting. Every answer I save reuses next time, so the second one is much faster than the first.Votes: 0GitHub stars: 117
- Acompanhar Prazos E AssinaturasMantenha o controle do que está pendente no lado jurídico. Escolha o que você precisa: cobrar assinaturas pendentes, registrar um contrato recém-assinado, ver quais prazos estão chegando, ou receber um resumo da semana toda segunda-feira. Eu mantenho uma lista contínua para que nada passe despercebido.Votes: 0GitHub stars: 117