1,133 tagged Security, measured the same way as everything else here.
Browse within: claude-code-plugin 230compliance 94agentic-ai 82fedramp 70claude-ai 50ai-tools 47skills 46ai-security 44agents 38auditing 37cmmc 37gdpr 36mcp-server 35data-privacy 33
Plugin Claude Code
Bundles 3 skills, 1 MCP server · 203 tokens together
MCP server for EVM security analysis, gas profiling, compiler diagnostics, and transaction simulation. Provides autonomous coding agents with deterministic, schema-validated tools for Ethereum smart contract development.
Plugin Claude Code
Bundles 2 skills, 2 hooks, 1 MCP server · 137 tokens together
Payment firewall for AI agents: a signed, verifiable verdict on every money-moving action. Blocks wrong/lookalike payee, over-cap, and duplicate-invoice fraud before it settles. Non-custodial, local-first.
cyanheads/osv-advisory-mcp-server
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Query OSV.dev for package vulnerabilities, batch-audit dependency lists, and fetch full advisory records via MCP. STDIO or Streamable HTTP.
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Offline methodology engine and payload workshop for authorized penetration testing, CTF, security research, and education.
cyanheads/sanctions-screening-mcp-server
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Screen names against the consolidated OFAC, EU, UK, and UN sanctions lists and resolve legal entities against GLEIF, fuzzy-matched offline over a local SQLite + FTS5 mirror. A screening aid, not a compliance determination.
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Search and audit CVEs by keyword, severity, CWE, CISA KEV status, and CPE via the NIST National Vulnerability Database. STDIO or Streamable HTTP.
cyanheads/attack-surface-mcp-server
Plugin Claude Code
Bundles 32 skills, 1 MCP server · 2,220 tokens together
Passive external attack-surface mapping: CT subdomains, DNS, TLS, HTTP posture, RDAP/WHOIS, Shodan via MCP. STDIO or Streamable HTTP.
Guruprasath-Annadurai/Whitepact
Plugin Cursor
AI governance for agent tool calls: trust scoring, PII/harmful-content guardrails, hallucination detection, and compliance checks (NIST AI RMF, EU AI Act, ISO 42001) via 27 read-only MCP tools.
Plugin Cursor
Bundles 1 skill, 1 MCP server · 41 tokens together
Know Your Agent: fail-closed eval (ALLOW | DENY | REQUIREAPPROVE), dual-plane host=ide|runtime, human approval. This plugin is a thin MCP gate — the control plane is the sole PEP.
Plugin Gemini CLI
Zero-trust AI agent governance for Gemini CLI. Adds ORGA runtime, Cedar policy enforcement, SchemaPin tool verification, and cryptographic audit trails to your development workflow.
Little-H-lying-flat/72stack-sec
Plugin Claude Code
Bundles 1 skill · 357 tokens together
A collection of workflows for finding security weaknesses in websites and services, including security-response programs, public testing programs, and bug bounties. The description does not provide enough detail about its individual tools or steps.
Plugin Claude Code
Bundles 3 skills · 197 tokens together
UniFi Protect MCP server — manage security cameras, NVR, recordings, and smart detections.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 29 tokens together
Free website privacy scanner to detect pre-consent cookies and trackers, CMP and consent controls, privacy policy, GDPR/ePrivacy and CCPA, and HTTPS/TLS signals.
jkanselaar/python-code-validator
Plugin Claude Code
Bundles 1 skill, 1 hook · 44 tokens together
Checks every Python file Claude writes, before you read it: syntax, lint, types, an AST security policy and a credential scan, with the exact fix when there is one.
Plugin Claude Code
Bundles 10 skills · 979 tokens together
Document fraud detection for manipulated, fake and AI-generated PDF and image documents, plus identity verification and KYC sessions, age verification, content moderation, face search, AutoDoc invitations, and webhook verification. Bundles the Bynn MCP server.
Plugin Claude Code
Bundles 1 skill · 54 tokens together
Preflight security for AI-agent development. Run holster guard . to get a RUN verdict and a SHARE verdict on a repo before you hand it to an AI agent, commit it, or share it — catches live API keys, MCP servers that run unpinned code, and credential files missing from .gitignore. Local-first; the repo never leaves yo.
Plugin Claude Code
Bundles 2 skills, 1 MCP server · 101 tokens together
Personalised developer security learning pathways from SecDim's challenges and courses.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 110 tokens together
logi Agent Approval Gate — request human approval on a user's phone before an AI agent performs a high-risk action (budget changes, production deploys, payments, mass communications).
joeyycli/constitution-lint-action
Plugin Claude Code
Bundles 1 command, 1 MCP server · 18 tokens together
Lint a CLAUDE.md-style agent constitution for missing operational guardrails — 10 heuristic checks (spend limits, injection defense, escalation path, secrets handling, ledger discipline, session ritual, referenced state files). Adds a /lint-constitution command.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 419 tokens together
Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 256 tokens together
Compliance evidence from AIops audit trails: HIPAA/PCI/SOC2/GDPR, OSCAL export, 19 tools.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 378 tokens together
Governed OPNsense + pfSense firewall ops: rules, NAT, VPN, DHCP, RCA. 35 tools.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 294 tokens together
Governed Keycloak + authentik identity ops: users, events, clients, MFA, RCA. 29 tools.
Plugin Claude Code
Scores the blast radius of a shell command before your agent runs it — advisory, never blocking. Same command, opposite score depending on what it would actually hit.
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: