Skip to content

Security

Protecting systems and data — vulnerability review, secrets, access control and hardening.

6 apps, 36 skills and 23 MCP servers tagged Security.

Best Security agent skills, ranked

Apps

All apps
Featured

Open-source, sandboxed AI agents for every employee, fronted by a gateway that injects scoped credentials so the agent never holds a password.

Automation & WorkflowsSubscription

App: Promptfoo

Promptfoo, Inc.

New

Open-source CLI for evaluating and red-teaming LLM apps: compare models side by side, assert on outputs in CI, and scan agents and RAG pipelines for jailbreaks and data leaks.

Coding & DevelopmentFreemium

Open-source dark-web threat intelligence: ask one question, get a sourced report, a searchable entity graph and exportable IOCs.

Data & AnalyticsFreemium

Microsoft's open-source, policy-driven sandbox SDK for running agents, model-generated code, tools and plugins with only the files and network access you grant.

Coding & DevelopmentFree

Security scanner and runtime monitor for AI agents that audits skills, MCP servers and CLI tools for malicious code and prompt injection.

Coding & DevelopmentFreemium

Deepfake detection for audio, video and images via API, meeting bots and a Chrome extension, from a former voice cloning company.

Audio & VoiceFreemium

Skills

All skills
Featured

Google's official skill for driving the gcloud CLI safely from an agent: validate every command against its own help text, cap the output, and refuse the operations that should never run unattended.

Featured

Auth0's official agent skill: a router that detects your framework and intent, then loads the right Auth0 guidance for login, MFA, Organizations, tenant audits, debugging or provider migration.

Skill: Solana Development

by Solana Foundation

New

The Solana Foundation's end-to-end Solana skill: opinionated defaults for @solana/kit clients and v1 transactions, wallet UIs, Anchor and Pinocchio programs, Surfpool/LiteSVM testing, security review, and guardrails against signing without approval.

OpenAI's skill for repository-grounded threat modelling: derive trust boundaries, assets and attacker capabilities from the actual code, rank abuse paths by likelihood and impact, and write a reviewable Markdown threat model.

Skill: Turnstile Spin

by Cloudflare

Turns “set up Turnstile” into a working end-to-end bot check — widget, frontend snippets, canonical server-side siteverify, and a real validation pass before it reports success.

Pillar Security's SAIL V2 framework as an agent skill: a 91-risk catalogue across seven lifecycle phases, for AI security gap assessments, roadmaps, and ISO 42001 / EU AI Act compliance checklists.

Skill: Zeroize Audit

by Trail of Bits

Finds secrets left in memory in C, C++ and Rust — including wipes the compiler deleted — and requires IR or assembly evidence before calling one optimized away.

Audits npm, PyPI and Go dependencies for advisories, abandoned upstreams, publisher concentration and install-time scripts — measured by scripts, not estimated.

Compiles cryptographic code and reads the emitted assembly for variable-time instructions, then triages which flagged operations actually touch secrets.

Trail of Bits' skill for writing production-quality Semgrep rules — pattern design, taint mode for data-flow bugs, and mandatory test-driven validation.

Harden a Twilio integration against credential leaks and fraud — API keys instead of auth tokens, webhook signature validation, geo-permissions, SMS pumping prevention and zero-downtime credential rotation.

Firebase's official red-team skill for auditing Firestore and Cloud Storage security rules — hunting privilege escalation, create/update bypasses and resource-exhaustion holes.

MCP servers

All MCP servers

MCP: Vanta

by Vanta

Featured

Vanta's official remote MCP server — query controls, tests, vendors, vulnerabilities and policies across SOC 2 and ISO 27001, and remediate failing tests from your agent.

MCP: HackerOne

by HackerOne

Featured

Official read-only MCP server for HackerOne bug bounty reports, programs, and remediation data.

Defensive MCP server and CLI that hardens your own release artifacts (JS bundles, Electron ASAR, WASM, SQLite, model files) against AI reverse-engineering agents.

MCP: Ghidra MCP

by bethington

New

MCP server and Ghidra extension with 219 tools for AI-assisted reverse engineering: decompile, rename, retype and comment, plus P-code emulation, live debugging and Ghidra Server workflows.

MCP: IDA Pro MCP

by mrexodia

New

Open-source MCP server that lets an agent drive IDA Pro for reverse engineering — decompile, trace cross-references, rename, retype, patch and debug — in the GUI or headless through idalib.

A native x64dbg plugin exposing 84 debugging tools and 22 event callbacks over HTTP, so an AI assistant can drive breakpoints, memory and disassembly directly.

JFrog's official remote MCP server: 100+ tools across Artifactory, Xray and Curation, hosted on JFrog Cloud with OAuth and no client install.

Vulnerability triage for AI agents: 28 security tools across 24 free intelligence sources — NVD, EPSS, CISA KEV, MITRE ATT&CK, Shodan and VirusTotal — behind a single triage_cve call.

MCP: Cloudsmith MCP

by Cloudsmith

Cloudsmith's official MCP server, built into its CLI: manage artifact repositories, packages and policies through an agent, with write operations off by default.

Automox's official MCP server for endpoint management — 130+ tools over devices, patches, policies, groups and audit data, self-hosted or on Automox's hosted endpoint.

MCP: Semgrep MCP

by Semgrep

Semgrep's official MCP server — scan code for security vulnerabilities, write and test custom rules, and pull findings from Semgrep Cloud, from inside an agent session.

Snyk's official MCP server, shipped inside the Snyk CLI: scan code, dependencies, containers and IaC for vulnerabilities, generate SBOMs and monitor projects from your agent.

Official SonarSource MCP server — pull code-quality issues, security hotspots, quality gates and rule explanations from SonarQube Cloud or Server into your agent.

Docker's official CLI plugin that runs MCP servers in isolated containers behind one gateway — secrets management, OAuth flows and a single config every client shares.

Related tags

Tags that appear alongside this one, ranked by how often.

All tags