Security agents

kidboy-man/vibe-engineering

Agent Claude Code

Security and data-safety review for backend/API/database changes, especially authz, tenant isolation, tokens/codes, billing, RLS, secrets, and unsafe logs.

Effulgent-Point/paw

Agent Claude Code

PHP/Laravel-specific reviewer — SQL injection, mass assignment, CSRF, N+1 Eloquent, auth middleware, type safety, queue idempotency.

vaquarkhan/compliance-agent-skills

Agent Claude Code

Simulates a CMMC Level 2 assessment perspective for organizations handling Controlled Unclassified Information (CUI) — not a C3PAO certification or SPRS submission.

hwchany0ung/claude-agent-playbook

Agent Claude Code

Use for OWASP Top 10 security audits, JWT/auth flow review, database RLS policy validation, API rate limiting checks, and vulnerability assessment. Read-only analysis agent — does NOT modify code. Use after major feature implementation or before production releases.

vignesh2027/AI-AGENT-SKILLS

Agent Claude Code

You are a Security Engineer conducting a security review. You apply adversarial thinking: assume malicious users, assume compromised dependencies, assume insider threats. Your goal is to find exploitable vulnerabilities, not just to find "bad practices.".

VoidTechnology/voidtech-claude-plugins

Agent Claude Code

A security-review agent for Voidtech Loop, a tool that runs commands and manages Git workspaces. It performs a read-only, adversarial review and reports only reproducible critical or high-severity problems.

Huleinpylo/kali-agents-mcp

Agent Claude Code

Use this agent to generate parsers for security tool outputs. Examples include:\n\n \nContext: Developer is integrating a new security tool into an MCP server.\nuser: "I need to parse nmap XML output to extract open ports and services."\nassistant: "I'll use the parser-generator agent to create a robust nmap XML…

xtofuub/frida-mcp-server

Agent Claude Code

Hunts client-side logic flaws in an attached iOS app — enumerates ObjC/Swift gate methods, traces them on real flows (human drives the UI), flips boolean returns, and verifies whether capability is actually gained. Use for the logic/runtime phase.

pixeleishen/wind-mcp-server

Agent Claude Code

Reviews code changes in this project for correctness, security, and adherence to project conventions. Use after writing or modifying TypeScript or Python files. Checks for known anti-patterns specific to this codebase.

boecht/birre

Agent Claude Code

BiRRe QA mode for tool validation and demonstration.

tealfabric/cursor-mcp-tealfabric

Agent Claude Code

Verify build, docs, and plugin metadata before publishing.

docevilOck/agent-skills-hook

Agent Claude Code

A code-review agent for C projects that checks coding standards, quality, security, architecture, performance, and unused or repeated code.

wardawgmalvicious/agent-config

Agent Claude Code

Security scan specialist. Use proactively before commits, during code reviews, or when asked to audit security. Scans for hardcoded credentials, secrets, injection risks, unsafe deserialization, overly permissive config, and risky Azure/cloud patterns. Returns findings with severity and file:line refs; does not modify…

Sequentum/sequentum-mcp

Agent Claude Code

Use this agent when you need to conduct comprehensive code reviews focusing on code quality, security vulnerabilities, and best practices. Specifically:\n\n \nContext: Developer has submitted a pull request with changes to critical authentication logic in a TypeScript backend service.\nuser: "Can you review this PR…

stevologic/security-recipes.ai

Agent Claude Code

Compare Codex, Claude Code, Cursor, Copilot, Devin, Shiba Studio, Hermes, and OpenClaw for AI vulnerability remediation with bounded instructions and review gates.

threadlinqs-cmd/Threadlinqs-Security-Detection-MCP

Agent Claude CodeCursor

Attack Range configuration and build specialist. Use to build custom ranges for specific detection testing scenarios.

KhaiTrang1995/claude-code-structure

Agent Claude Code

Specialized sub-agent for security analysis with an isolated context window.

vindm/dotclaude

Agent Claude Code

Database integrity auditor — queries the persistent store for incomplete enrichment, orphaned references, stuck state-machine rows, cross-tenant leaks, and invariant violations. Read-only; produces a Good/Gaps/Critical health report with example IDs, diagnostic hypotheses, and severity tiers. Run after pipeline…

ReviewToolkits/cpython-security-toolkit

Agent Claude Code

Analyzes CPython security fix commits and checks whether the fix was applied to all code paths through the same invariant. The most important agent for preventing second-round CVEs. Invoke after identifying a security fix commit or when reviewing recent type-security labeled changes.

Firmislabs/firmis-scanner

Agent Claude Code

Collects and exfiltrates sensitive data.

bhuvangupta/vapt-claude

Agent Claude Code

You are an authentication and access control testing specialist. You are one of 3 parallel agents in Wave 3 of the VAPT audit.

guib1/red-team-docker

Agent Claude Code

Autonomous hunt loop agent. Runs the full hunt cycle (scope → recon → rank → hunt → validate → report) without stopping for approval at each step. Configurable checkpoints (--paranoid, --normal, --yolo). Uses scopechecker.py for deterministic scope safety on every outbound request. Logs all requests to audit.jsonl.…

msopariw/GitHubCopilotDemo

Agent Claude Code

Code reviewer agent that checks code quality, security, and best practices for the Todo app.

zexion7873/copilot-setting

Agent Claude Code

Perform code reviews, security audits (OWASP Top 10), SQL and schema migration reviews, and Maven pom.xml dependency checks (within code review). Each review mode follows its own checklist and severity model.