26,946 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Cursor rule Cursor
Run a full-spectrum, multi-agent audit covering every layer of the application: architecture, implementation, testing, security, frontend/UX, product alignment, and blind code review. All rounds run in parallel — contamination is prevented by instruction, not by timing. Phase 2 begins only after all active rounds…
myclaude-sh/myclaude-creator-engine
Skill Claude Code
SAST security audit: STRIDE threat model, 300+ vuln patterns, 8 compliance frameworks, auto-fix, hardening. Use when: audit code, find vulnerabilities, compliance check, threat model, secrets scan, CVE review. NOT for: DAST, pentesting.
Ansvar-Systems/EU_compliance_MCP
MCP server Claude CodeCodexCursor +2
Query 47 EU regulations (GDPR, NIS2, DORA, AI Act) - 2,438 articles, 3,712 recitals, ISO 27001. Runs locally from the @ansvar/eu-regulations-mcp npm package.
Plugin Claude Code
Bundles 32 skills, 15 commands, 9 agents · 2,759 tokens together
Claude Code plugin for whitebox security review. Stable: deterministic offline quick scan, shared findings.json with stable keys and hotspot-aware findings, SARIF/Markdown/HTML/bundle reports, suppressions, CI fail-on gate, Kuzushi parity. Beta: deep profile with Joern/CodeQL/Slither/Trivy/Checkov when installed.…
Plugin Claude Code
Bundles 1 skill · 128 tokens together
Security audit and hardening for vibe-coded SaaS apps. Walks the 50 most common ways AI-generated apps get owned and produces a prioritized fix list.
Skill Claude CodeCodex
Understands nono security sandbox constraints. Use when running inside a nono sandbox, when tool operations fail with permission errors, or when the user asks about sandbox capabilities.
elastic/example-mcp-app-security
Skill Claude CodeCodex ✓ vendor
Triage Elastic Security Attack Discovery findings — fetch correlated attack narratives, assess confidence with entity risk and rule frequency signals, and present an interactive triage dashboard for approval, case creation, and acknowledgment. Use when triaging attack discoveries, reviewing correlated attacks…
MCP server Claude CodeCodexCursor +2
Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents. Runs locally from the @agentkitai/agentlens-mcp npm package.
crowdsecurity/crowdsec-local-mcp
MCP server Claude CodeCodexCursor +2
An MCP exposing prompts and tools to help users write WAF rules, scenarios etc. Runs locally from the crowdsec-local-mcp Python package.
Skill Claude Code
Review MCP server specifications and updates for compliance, security, and quality. Use when evaluating server.json files, PRs adding/updating servers, or assessing MCP server changes. NOT for creating new entries (use add-mcp-server instead).
afiqiqmal/claude-security-audit
Command Claude Code
Run a comprehensive white-box and gray-box security audit with OWASP Top 10:2025, CWE, NIST CSF 2.0, SANS Top 25, ASVS, PCI DSS, MITRE ATT&CK, SOC 2 and ISO 27001 mapping. Shows findings by default. Append --fix to include remediation code blocks.
Skill Codex
Gate dependency installs (npm/pip/cargo/go/gem/maven/nuget) with OSV-backed advisory checks, approved-spec ledger, and post-install reorg rollback. Run safedeps check @ before any install command.
Skill Codex needs its repo
Create and manage isolated microsandbox microVMs for safe code execution, testing, development, and agent workflows. Use when the user needs to run untrusted code, create ephemeral or persistent sandboxes, execute commands, copy files, inspect logs and metrics, configure networking or secrets, mount volumes, manage…
Skill Codex
Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection signature detection, and adversarial robustness scoring.
UnboundCompute/security-agent-skills
Plugin Claude Code
Bundles 194 skills · 32,602 tokens together
Security-testing methodology as portable agent skills, spanning white-box bug hunting, AI-agent and LLM red-teaming, cloud identity and CI/CD trust, client-app trust surfaces across browser and editor extensions and Electron, wire-protocol and token trust across gRPC, WebSocket, and JWT, enterprise identity lifecycle…
Plugin Claude Code ✓ vendor
Bundles 5 skills · 888 tokens together
Technical AWS solutions for the problems startups get stuck on, from the AWS Startups Solution Architecture team. Multi-tenant SaaS isolation enforced in IAM rather than application code, and running a judgment agent such as an LLM reviewer inside a CI path. Startup here means the technical constraints are startup…
Njones17/AI-agent-master-cyber-skills-list
Skill Claude CodeCodex
Use when planning, scoping, or executing a comprehensive security assessment, penetration test, red team engagement, or security audit. Use when the user needs to coordinate multiple security testing activities, define assessment scope and rules of engagement, perform threat modeling, rate risk using CVSS, map…
Plugin Claude Code
Bundles 38 skills, 4 MCP servers · 695 tokens together
Offline AI/LLM security scanner: prompt injection, MCP command injection and tool poisoning, RAG leaks, poisoned Agent Skills. Scan code, or check a skill/MCP server before you install it.
MCP server Claude CodeCodexCursor +2
MCP server for CTFd that lets regular users browse challenges, manage dynamic instances, and submit flags. Runs locally from the ctfd-mcp Python package.
Skill Claude CodeCodex
Use to inventory and risk-classify every API key and user-managed service-account key across all accessible GCP projects. READ-ONLY — does not mutate cloud state. Use standalone, or as Phase 1a of the gcp-ironclad driver.
Plugin Claude Code
Bundles 4 skills · 131 tokens together
Offensive security toolkit for Claude Code — Neo4j intel graph, strategic compaction, multi-agent orchestration, and post-engagement debriefs.
Agent Claude Code
Full security audit including static and dynamic red-team style checks.
NikolasMarkou/epistemic-deconstructor
Skill Claude CodeCodex
Systematic reverse engineering of unknown systems using scientific methodology. Use when: (1) Black-box analysis, (2) Competitive intelligence, (3) Security analysis, (4) Forensics, (5) Building predictive models. Features 6-phase protocol with a mandatory abductive expansion sub-phase, Bayesian inference…
trnt-ai/trent-openclaw-security-assessment
Skill Claude Code
Assess your Agent deployment against security risks using Trent.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: