security

Audit one approved local Git repository through a bounded, read-only MCP interface.

Triage Dependabot alerts and recommend safe, evidence-based dependency updates.

Sourcery security findings for AI coding agents: triage and minimal-change remediation via the public Sourcery API (12…

Set up, run and fix MegaLinter on any repository: 100+ linters for 69+ languages, 23+ formats and 21+ tooling formats,…

Adam's general-purpose skills, safe anywhere including cloud sessions: writing voice, GitHub Actions debugging and…

Verify Adverserial confidential-inference attestation before a Codex session uses the endpoint.

Code and Rust reviews, test-writing guidance, backporting, security audits, project scaffolding, and documentation…

Scan an MCP server, package, or GitHub repo for a signed 0-100 trust score before your agent connects to it.

Agent-facing skills for vetting AI skills, MCP servers, and agent configs with vettd.

Project-agnostic security skills for repository audits, diff review, deterministic scanning, supply chain, threat…

GitHub Actions hardening, CI-efficiency, and runtime-upgrade skills with a report-only workflow reviewer.

Apache Magpie — a reusable, governance-agnostic framework of agentic skills for maintaining open-source projects:…

Behavioral drift detection for autonomous AI agents.

GitHub Actions diagnosis and review skills for runtime failures, security, optimization, and architecture.

Add Auth0 authentication to any app — login, MFA, SSO, Organizations, RBAC, ACUL, custom domains, and branding. Debug…

Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run…

[Deprecated — superseded by the aws-well-architected-review skill in Agent Toolkit for AWS:…

Modern .NET 10 / C# 14 house-rules bundle for SessionBoard-style minimal APIs: an add-endpoint skill, a read-only…

Aevral is an AI security reviewer for GitHub pull requests. Setup skill for the Aevral GitHub App: reviews look for…

Blaxel agent skills and MCP server for building and deploying AI workloads. Includes the Blaxel SDK skill for creating…

Local-first privacy posture auditing, forensic residue analysis, and verified remediation

Codex-native skills and specialist agents for disciplined software delivery.

Intelligent permission gate for Claude Code shell, file, search, Skill, and MCP tool surfaces. AST-parses Bash…

Read-only, evidence-backed technical project review across applicable architecture, code, security, delivery,…

Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run…

Connect your agent to CloudPeek, the AI security teammate. Triage the 5% of alerts that matter, run investigations, and…

Clover reviews every spec before implementation starts, hands back the security requirements it is missing, and blocks…

Stateful integrity verification for every Codex tool call: argument classification, output scanning, sensitive-data…

CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action…

Findings-to-Fix builds on Checkmarx One Triage Assist and Remediation Assist. Triage Assist has already evaluated the…

Validated Cybret API and app security findings, with remediation guidance, for coding agents.

Custom agents that have been created by GitHub partners

Production C++ for QKD ground-segment systems: implement, build, and multi-lens review.

Datadog API CLI with 49 command groups, 300+ subcommands. Skills and domain agents for monitoring, logs, APM, security,…

A set of Copilot skills for capturing, documenting, and implementing repository context.

Read-only first-party Aperture Wallet product, security, network, release, and Journal knowledge for AI agents.

Custom agents that have been created by GitHub partners

End-to-end guidance for full-stack applications, from focused context, requirements, and planning through architecture,…

LyraShield AI security and release-assurance plugin

A coordinated product and engineering team for taking software from market research through secure implementation.

Endor Labs security workflow skills, agents, rules, and hooks for GitHub Copilot. Requires only the endorctl binary: no…

Comprehensive application security toolbox for Codex. 62 skills across 8 frameworks (OWASP Top 10, OWASP API Top 10,…

Provider-agnostic VDH/VVS security research plugin (MiniMax, Anthropic, OpenAI, OpenRouter, DeepSeek, Google,…

GitHub Copilot CLIを使って観点別に並列コードレビューを実行するプラグイン。差分やPRを複数の専門サブエージェントがcopilot -pで同時にレビューする。

Measure the MCP servers your agent calls, record the tool surface you approved, and refuse a changed tool until a…

Finds secrets and personal data locally, in your prompts and in the tool results the agent reads, and tells you what it…

Model Context Protocol (MCP) security auditing for RCE, STDIO injection, and supply chain vulnerabilities.

Custom agents that have been created by GitHub partners

Agent Looker safety guardrails for AI agents: URL safety checks, external text safety checks, and proactive risk…

Guard Core security tools: validate fastapi-guard and guard-core configs, search the Guard documentation, resolve…

Evidence-backed STRIDE threat modeling with Strider, deterministic validation, and optional tmforge .tm7 authoring.

Codex marketplace bundle for secure development, OWASP, risk gates, and web identity.

Analyze domains, hunt lookalikes and search certificate transparency; triage your organization's detections and alerts,…

Risk-based Kotlin review agents for READMEs, tests, architecture, domain behavior, concurrency, API and data…

Vendor-neutralなState Machine、Machine Floor、REFINE連動のProfile自動判定、Capability SkillsでCodex/Devin系Agentを制御するSuzumemo Agent…

Credential broker CLI for AI agents. Injects credentials into subprocess memory — agent never sees plaintext values.

Production-safety audits for AI-generated code, with a fix for every finding.

Project fitness review skills (architecture, security, reliability, testing, performance, algorithms, data,…

Portable AI agent harness — curated review/build/test agents, secret-hardening + worktree + plan-gate hooks, and…

Deployment-exposure guides for services AI-assisted projects commonly run: TLS, authentication, MFA, secrets, and…

Dependency vulnerability triage: scan package.json and requirements.txt against OSV.dev, rank findings by severity, and…

Skills for AI coding agents: code review, test writing, design docs, debugging, security and dependency audits, git…

Proving the system works and keeping the repo presentable: LLM evaluation, test strategy, E2E acceptance suites,…

KOSIF Think Pro 3 — think-first orchestration plus measured expert studio: image analysis, image generation, lighting,…

Structural code quality metrics, lattice verification, and refactor loops for agent-written code.

Prompt-injection and dangerous-action guard for coding agents, powered by Jev.

A human-governed, resumable engineering workflow for coding agents.

Agentic multi-perspective code review with adversarial validation.

Check npm packages and install dependencies through SafeInstall's artifact-bound policy gate.

AGT governance hooks for the OpenAI Codex CLI

Repository-specific workflow for key-manager Go code and SSH, GPG, PQC, TLS, filesystem, and subprocess security…

Checks the infrastructure commands Copilot wants to run (kubectl, terraform/tofu, aws/az/gcloud, helm, argocd, git,…

Evidence-based debugging for AI agents: map the project, run it, trace what actually executes, then report findings…

Discover, security-vet, and install GitHub Copilot skills and extensions with explicit provenance, integrity, and risk…

Production-readiness checks for AI-built apps: scan the repository your builder syncs to, fix what would break, and…

Run NebuSec Platform code and cloud security workflows from an agent.

Vendor-neutral React Native skills for developers and AI agents. Spec/Skill-Driven Development from spec authoring…

Scan code, dependencies, containers and IaC with Snyk's first-party MCP server (shipped inside the pinned Snyk CLI),…

Investigate alerts, devices and incidents on your own Darktrace Threat Visualizer appliance through a local MCP server:…

Application-security review skill for codebases and pull requests you are authorized to assess. Maps trust boundaries,…

Review pull requests, fix issues, implement features, refactor code, upgrade dependencies, investigate CI failures,…

Ten evidence-led checks for understanding what AI work touched, changed, remembered, and actually completed.

Set up, run and fix MegaLinter on any repository: 100+ linters for 69+ languages, 23+ formats and 21+ tooling formats,…

Comprehensive Power BI development resources including data modeling, DAX optimization, performance tuning,…

Octo Industries engineering standards: secure-by-default guidance and a pre-merge checklist.

Skills for using the Pixee CLI: authentication, scans, workflows, repositories, findings, and API access.

Audit Omarchy plugins using reviewer-attributed marketplace findings and regression checks.

Gates every Edit/Write in this session against vord's Agent Permission Policy (vord-policy.toml) before the bytes reach…

Risk-adaptive software engineering operating skill for reliable AI-assisted vibe coding, architecture, staged…

Custom agents that have been created by GitHub partners

Export and analyze Rapid7 InsightVM vulnerability, asset, policy, and remediation data via SQL queries

損害控制 (Damage Control) 安全系統 - 透過 PreToolUse 鉤子封鎖危險指令並保護敏感檔案

Screen prompts, skills and MCP tools with TypeSafe judgments and configurable reasoning models.

Evaluate signup privacy risks and public security evidence before sharing personal information with a service.

Kiro configuration ported to GitHub Copilot: agent skills, custom agents (with subagents + handoffs), and MCP servers.

Reusable Copilot plugin for reviewing Gravitee API definitions against API governance rules.

Ship software and lead the people who build it — git workflows, architecture decisions, code quality, testing, APIs,…

Security guardian: blocks secrets and dangerous commands before they land, scans for OWASP Top 10 patterns, and guides…

Safe Postgres access for AI agents. Scoped credentials, read-only by default, table and column allowlists, PII masking,…

Skarn for Cursor: audit your AI coding sessions and assistant configs for leaked credentials and risky configuration,…

Review and generate production-quality UI with anti-vibecoding, accessibility, security, responsive, reliability, and…

Security analysis skills: trust boundaries, secrets, authorization, input validation.

Team security standards for developers and AI agents: application security, identity, CORS, secrets, threat modeling,…

Better Auth skills for scaffolding, configuring, and hardening authentication in TypeScript/JavaScript apps.

Turn rough instructions into optimized, evidence-based prompts for AI agents, coding agents, tools, eval graders, and…

Website QA tool built for coding agents (Claude Code, Cursor). 260+ rules across SEO, performance, security,…

Plugin de ingenieria de software: 8 agentes de nucleo, Selina si hay frontend y Lucius bajo demanda. Memoria…

Static multi-ecosystem dependency evidence, security, SBOM, and update-impact analysis for coding agents.

Stripe agent plugin with skills for Stripe integrations including best practices, API and SDK upgrade guidance, and a…

Query Sumo Logic logs, alerts, dashboards, and SIEM insights directly from Copilot. Connects to the Sumo Logic MCP…

Coverage, security and code quality for coding agents.

Evidence-driven code audits, root-cause diagnosis, simplification, remediation, improvement plans, and repository…

Security skills — OWASP audits, secret scanning, and dependency supply-chain hardening

Review and implement fail-closed boundaries around consequential AI-agent actions.

Explore, run, and build Tines 3B workflows from your agent.

Trent, an AI security engineer. Review code, plans and configs for security problems, run threat models over a repo or…

Threat modeling, secure coding, and severity-classified security review for software and AI-agent changes, grounded in…

Vet an MCP server before you install it: see what each tool can execute, read, write, and send, using reachscan's…

Scheduled findings that open PRs/issues, deliberately capped and conservative: audit-architecture (tech-debt sweep),…

Investigation playbooks for the WhisperGraph internet-infrastructure graph: indicator triage that reads coverage before…

Offensive security case ledger for Pi Agent — evidence tracking with machine-verified PoC gates.

Deterministic pre-execution policy enforcement for coding-agent actions.

Make your coding agents automatically self-improve. Enforce your coding standards while your developers keep using…

GRC compliance review for your pull requests. heyGRC reviews each PR against ISO 27001, SOC 2, GDPR, DORA, NIS 2, the…

Look up CVEs and CWEs from CloudPeek's indexed Open Knowledge Format corpus. Deterministic, source-grounded…

Comprehensive Power BI development resources including data modeling, DAX optimization, performance tuning,…

Comprehensive Power BI development resources including data modeling, DAX optimization, performance tuning,…

Scan a software repository for ISO 27001:2022 compliance of its software development controls (Annex A 8.4, 8.25–8.33).…

GitHub Issueの作成・一覧・処理を自動化するプラグイン。プロンプトインジェクション対策として、自身が作成したIssueまたは承認済みIssueのみを処理する安全機構を備える。

Comprehensive Power BI development resources including data modeling, DAX optimization, performance tuning,…

Use this plugin for application, host, and supply-chain security control workflows.

Comprehensive Power BI development resources including data modeling, DAX optimization, performance tuning,…

Security guardrails for AI agents: blocks destructive commands and secret access with hooks, scans for secrets and…

XPI — offensive security tools for Pi Agent and OMP (fork): casefile ledger with honest-PoC gates, web lookup, exploit…

Security frameworks, accessibility guidelines, performance optimization, and code quality best practices for building…

Security frameworks, accessibility guidelines, performance optimization, and code quality best practices for building…

Cloudflare のソース主導セキュリティ監査。通常は関連ガイダンス、明示されたコードベース監査・包括的レビュー・報告成果物の依頼では六段階の検証と報告を実行する。

Security frameworks, accessibility guidelines, performance optimization, and code quality best practices for building…

Use this plugin for cybersecurity lab workflows for purple-team validation, mobile security, NetHunter research, and…

Security frameworks, accessibility guidelines, performance optimization, and code quality best practices for building…

7 specialized agents covering the full software development lifecycle from UX design and architecture to security and…

7 specialized agents covering the full software development lifecycle from UX design and architecture to security and…

7 specialized agents covering the full software development lifecycle from UX design and architecture to security and…

7 specialized agents covering the full software development lifecycle from UX design and architecture to security and…