Security

Security engineering for web applications, APIs, and the AI agents and tools around them. Use to audit code or architecture, check whether a suspected flaw is exploitable, threat-model a feature, or harden sign-in, sessions, OAuth, access control and tenant isolation, injection, XSS, CSRF, SSRF, file uploads, cryptography and secrets, webhooks, race conditions, dependencies and CI/CD, WordPress, and prompt injection or tool permissions in LLM agents; also for "is this secure", leaked keys, dependency alerts, and incident triage. Traces real attack paths from attacker input to impact, reports e

9 stars 2 forksSecurity

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add prangishviliAbe/agent-skills --skill security
Manual install
git clone --depth 1 https://github.com/prangishviliAbe/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/security ~/.claude/skills/security

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Application and AI Agent Security

Find the places where an attacker's input crosses a trust boundary and reaches something valuable, prove the path, and close it with the smallest change that holds. No system is "secure" in the abstract; a review states what was examined, what was found, and what was not covered.

## Scope and authorization

Before anything else, establish: what is in scope (code, environment, accounts), what the user owns or is authorized to test, and whether the task is review only or review and fix. Read code and test locally or on systems the user controls. Do not send payloads to third-party or production systems, scan networks, or use discovered credentials without explicit authorization. Never print live secrets; refer to them by location.

## Method

1. **Map.** List entry points (routes, actions, webhooks, queues, file uploads, agent tools), the identities that can reach each, and the assets behind them (data, money, credentials, compute).
2. **Trace.** For each sensitive operation, follow attacker-controlled input from entry to sink. Note every check on the way and whether it runs on the server, on the right identity, and before the effect.
3. **Decide.** A finding needs a plausible path: who can do it, with what input, bypassing which defense, to what impact. A pattern match without a path is a lead, not a finding.
4. **Rank.** Severity comes from impact and reachability together, with the reasoning stated.
Read the full skill on GitHub

Details

Skill name
security
Path
security/SKILL.md
Repo updated
14 November 2026

FAQ

What does the Security skill do?

Security engineering for web applications, APIs, and the AI agents and tools around them. Use to audit code or architecture, check whether a suspected flaw is exploitable, threat-model a feature, or harden sign-in, sessions, OAuth, access control and tenant isolation, injection, XSS, CSRF, SSRF, file uploads, cryptography and secrets, webhooks, race conditions, dependencies and CI/CD, WordPress, and prompt injection or tool permissions in LLM agents; also for "is this secure", leaked keys, dependency alerts, and incident triage. Traces real attack paths from attacker input to impact, reports e

How do I install the Security skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add prangishviliAbe/agent-skills --skill security. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Security popular?

It lives in prangishviliAbe/agent-skills, which has 9 GitHub stars and 2 forks.

Related skills

Anti AI Slop Design

9

prangishviliAbe/agent-skills

Design, refine, implement, or critique websites, landing pages, dashboards, apps, and components so nothing looks AI-generated or templated. Use for "looks AI", "too generic", "make it premium", "make it look better", art direction, redesigns, visual polish, a page or component designed from scratch, or a review of how a UI looks, including Georgian and multilingual layouts. Covers every layer where slop appears: page structure, typography, color, spacing, surfaces, icons, imagery, copy, motion, and the code that produces them. Replaces default choices with decisions derived from the subject,

AI, LLMs & Agents

Premium Web Motion

9

prangishviliAbe/agent-skills

Design, implement, tune, and debug web motion: hover and press feedback, menus, dialogs, drawers, accordions, toasts, page and view transitions, list reordering, drag and gesture feedback, scroll-driven effects, loading states, and motion tokens, in CSS, the Web Animations API, React, Motion, GSAP, and component libraries. Use for "add animation", "make it feel smoother or more premium", janky, slow, or glitchy transitions, animations that break when interrupted, reduced-motion support, or a review of how a UI moves. Gives every motion a purpose, exact duration and easing, interruption safety,

Frontend & Design

Token Efficiency

9

prangishviliAbe/agent-skills

Make responses and agent work cheaper to read and to run without losing correctness: concise answers, TL;DR, brief status updates and final summaries, just-the-code replies, and lean tool use that avoids rereading files, dumping logs, and repeating checks. Use whenever the user asks to be brief, short, or concise, says "less text", "just the code", "TLDR", or "save tokens", complains about limits or cost, or runs a long session where context is filling up. Puts the answer first, keeps the evidence, failures, and caveats that change decisions, replies in the user's language, and never trades co

Software Development

Security Audit

9

DIL8654/claude-code-dotnet-template

Review .NET services for safe defaults in input handling, authentication, authorization, secret management, logging exposure, and configuration hygiene. Use before release, during reviews, or when hardening an API or integration.

Security

Token Security Analyzer

9

coinpaprika/claude-marketplace

Analyze tokens for security risks, scams, and honeypots. Activates when users share token addresses, ask about token safety, or request honeypot/rug pull analysis across 36 chains.

Security

Re Electron Skill

10

iceman1001/awesome_rfid_claude_skills

Electron application reverse engineering — ASAR unpacking, webpack bundle analysis, auth/payment logic discovery, IPC channel mapping, and client-side authorization bypass analysis. Use when the user needs to: reverse engineer an Electron app (.deb/.dmg/.exe), analyze auth/subscription/license logic in Electron apps, map IPC channels between main and renderer processes, identify client-side enforcement vulnerabilities (CWE-602), or perform security audit of Electron-based desktop applications for CTF or research.

Security

Browse the most popular Claude skills, all security skills, or write your own with the skills generator.