Security plugins

cylestio/agent-inspector

Plugin Claude Code

Security analysis plugins for AI agents by Cylestio.

cylestio/agent-inspector

Plugin Claude Code

AI Agent Security Analysis - scan, fix, analyze, and report on AI agent vulnerabilities using OWASP LLM Top 10.

pablo-albaladejo/kaiord

Plugin Claude Code

Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns.

tr4m0ryp/shor

Plugin Claude Code

Shor — autonomous AI web pentester. Provides the /shor-setup slash-command: an interactive wizard that guides you from zero to a running scan (black-box or white-box, GCP deployment included).

harish-garg/security-scanner-plugin

Plugin Claude Code

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

kapital-legal/claude-for-tr-legal

Plugin Claude Code

KVKK m.10 aydınlatma metni üretir, ilgili kişi başvurularını (KVKK m.13/2 30 günlük süre içinde) yanıtlar, VERBİS uyumunu kontrol eder, veri ihlali triajı yapar (72 saatlik bildirim — KVKK m.12/5 + Kurul'un 24.01.2019 tarih ve 2019/10 sayılı kararı), KVKK iyi uygulama düzeyinde risk değerlendirmesi üretir ve…

brandondees/code-quality-atlas

Plugin Claude Code

A research-derived suite of 41 code-review and maintenance lenses covering correctness, readability, structure, security, performance, tests, migrations, accessibility, observability, LLM and agentic/tool-use safety, install/upgrade experience, authored-artifact conventions (e.g. SKILL.md), and repo-wide audits…

ScopeBlind/scopeblind-gateway

Plugin Claude Code

Fail-closed Cedar policy gate plus Ed25519 signed receipts for AI agent tool calls. Blocks what breaks the rules before it runs, denies on any policy error, and proves the gate is live with a startup self-test.

ScopeBlind/scopeblind-gateway

Plugin Claude Code

Offline verifier for signed receipts, audit bundles, and trust artifacts. Ed25519 + JCS, no accounts, no network calls. Verify what an agent's gate decided without trusting the operator.

CrowdStrike/crowdstrike-mcp-skills

Plugin Claude Code

Configure the CrowdStrike Falcon MCP server with OAuth2 authentication using client credentials.

IvanBBaev/servicenow-mcp-ai

Plugin Claude Code

Drive ServiceNow from your AI assistant — 67 tools over the full REST surface, with plan-and-apply write safety, capability preflight and an ACL security scan.

miclivne/oc-security-audit

Plugin Claude Code

Pre-launch security audit for web apps. Runs OWASP checks via shell scripts, then AI analyzes findings. Covers rate limiting, hosting bypass, data exposure, headers, session security, AI risks.

eyesecurity/skills

Plugin Claude Code

EU compliance enforcement for AI agents — NIS2, GDPR, ISO 27001.

anmolnagpal/devops-skills

Plugin Claude Code

Team DevOps review and scaffolding skills: Terraform (source and plan), Kubernetes/Helm, Docker, GitHub Actions, GitLab CI, Argo CD/Flux, AWS FinOps, OWASP and application security, observability, incident runbooks, deployment gating, and ADRs. Findings carry shared auditkit rule IDs.

luiseiman/dotforge

Plugin Claude Code

Behavior governance for Claude Code — declarative runtime policies on tool calls (search-first, no-destructive-git, verify-before-done, …) compiled to PreToolUse hooks, plus configuration governance: 18 skills, 7 agents, 16 stacks, audit scoring, practices pipeline.

andypitcher/ponytail-sec

Plugin Claude Code

Ponytail security companion and audit: diff-scoped hardening for active development, plus full-project security scans.

polygraphso/litmus

Plugin Claude Code

Grade and verify MCP servers A–F with the open polygraph litmus — tool-output injection, egress, sensitive-data, and adversarial-input checks. Bundles the polygraph skill, the polygraph-litmus MCP server, and /polygraph:grade · /polygraph:check.

zyx77550/sparda

Plugin Claude Code

The behavior gate for AI edits — proves each edit lost no auth guard, dropped no route, and grew no blast radius. Deterministic, <2s, offline, zero API key.

geniro-io/geniro-claude-harness

Plugin Claude Code

Production-grade Claude Code harness with AI-driven setup, multi-agent skills, and safety hooks. Includes /setup for project-tailored configuration.

Peaky8linders/specter-oss

Plugin Claude Code

Specter — EU AI Act compliance toolkit. Validate citations against the canonical 113-article + 13-annex catalog, query the four-axis agentic compound-risk taxonomy, look up role obligations, and run the LLM-as-Judge reward-hack detector on proposed remediation tasks.

tabnine/skills

Plugin Claude Code

Context Engine CLI (ctx-cli) as focused skills — guided tenant onboarding, code & knowledge-graph search, service investigation, CVE & SAST triage with ready-to-apply fixes, and coding-guideline checks.

eriknewton/sanctuary-framework

Plugin Claude Code

The open source standard for secure, private AI: operating-system enforcement is live on macOS today; Linux and Windows are not live enforcement yet, and your data stays under your own keys with current portability bounds called out in the Assurance Matrix. Wraps any MCP-compatible agent with encrypted state, approval.

ahernandez-developer/claude-crap

Plugin Claude Code

Deterministic Quality Assurance plugin for Claude Code. Wraps every Write / Edit / Bash tool call with a PreToolUse gatekeeper, a PostToolUse verifier, and a Stop quality gate backed by CRAP index, Technical Debt Ratio, tree-sitter AST metrics, and SARIF 2.1.0 reports. Forbids the agent from writing functional code…

Ap6pack/outrider-recon

Plugin Claude Code

Claude-native authorized external recon and ASM methodology bundle with 90 documented capabilities across 11 skills, deterministic Python controls, an optional loopback-only limited-control web plane, explicit human-reviewed finding promotion, and optional fixed policy-gated MCP enrichment. It does not provide…