Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Guides compliance with Australia's Privacy Act 1988 including the 2024 reform amendments. Covers automated decision-making transparency, children's privacy code, individual rights expansion, enforcement strengthening, and the Australian Privacy Principles (APPs). Keywords: Australia Privacy Act, APPs, OAIC, automated decisions, children privacy code, privacy reform.
Use this skill when reviewing BoxLang code or applications for security vulnerabilities, configuring security settings, preventing injection attacks, handling file uploads safely, managing secrets, or applying secure coding patterns drawn from OWASP Top 10 and CFML/Java security history.
Executes the GDPR Article 33 mandatory breach notification to the supervisory authority within 72 hours of becoming aware of a personal data breach. Covers required notification content, deadline calculation, risk assessment for notification threshold, and DPO involvement. Keywords: GDPR, Article 33, breach notification, 72 hours, supervisory authority, DPO, EDPB.
Guides compliance with Canada's Personal Information Protection and Electronic Documents Act (PIPEDA, S.C. 2000, c. 5). Covers the 10 fair information principles in Schedule 1, consent requirements, cross-border transfer obligations, breach notification under Division 1.1, and OPC enforcement. Keywords: PIPEDA, Canada privacy, fair information principles, OPC, breach notification, cross-border transfer, consent.
Given a Chrome Releases blog post URL (chromereleases.googleblog.com), extract every CVE/bug and find the underlying Gerrit CL that fixed it by searching the local Chromium checkout and sub-repos. Use when asked to map Chrome security release notes to fixing CLs, or to find which commits correspond to CVEs in a Chrome stable update.
Use when inspecting or changing anything in a Cloudflare account as an agent — DNS records, WAF custom rules, bot settings, redirect, transform, cache or page rules, zone settings, tunnels, Workers, Pages, R2 or analytics. Reads go through a local read-only API token that the agent never sees. Changes are proposed for the human to make in the dashboard, or applied through an approval step when the user has deliberately stored a write token.
Chain-of-Thought (CoT) injection attack methodology. Triggered when a target system uses a ReAct/CoT framework for multi-step reasoning, an agent relies on intermediate reasoning results to make decisions, or the integrity of the chain of thought needs to be tested. Covers: chain-of-thought interference injection (forging intermediate agent results), chain-of-thought manipulation injection (skipping verification steps to directly dispatch sensitive operations), and query injection (injecting malicious query statements into a data-query agent).
Guidance for Microsoft Defender Threat Intelligence (Defender TI) and Microsoft Defender Vulnerability Management (MDVM) — the threat-and-vulnerability layer of Defender XDR. Covers MDVM exposure score, CVE prioritization with threat insights and active campaigns, security baselines (CIS/STIG), browser-extension and certificate inventory, network share assessment, hardware/firmware inventory, security recommendations and remediation tasks (Intune integration), and Defender TI for adversary-tracked indicators, intel profiles, infrastructure pivoting, and MDTI APIs. WHEN: Defender Vulnerability Management, MDVM, MDVM add-on, exposure score, threat-aware vulnerability prioritization, CIS benchmark CVEs, security baselines assessment, browser extension inventory, firmware vuln, Microsoft Defender Threat Intelligence, MDTI, intel profiles, threat actor tracking, IOC pivoting, MDTI API, threat hunting with intel. DO NOT USE for endpoint EDR config (use defender-for-endpoint), Sentinel detections (use sentinel-detection-engineering), or external asset discovery (use defender-easm).
Periodic dependency review for Node.js/pnpm projects — outdated package triage, security audit, update batching strategy (patch/minor/major), validation checklist. Run monthly or before major releases. Use when asked to review or update dependencies in a repo.
Incident response methodology. Use when a target host is suspected of being compromised, when backdoors/trojans/suspicious processes/suspicious accounts need to be investigated, or when security incident tracing and analysis is required. Covers account auditing, process investigation, network connection analysis, startup item/scheduled task checks, log analysis, and Rootkit detection on both Linux and Windows.
Guidance for Microsoft Entra workload identities — managed identities, service principals, and workload identity federation. Covers system-assigned vs user-assigned managed identity, federated credentials (GitHub Actions, Azure DevOps, Kubernetes, other OIDC issuers) to eliminate secrets, Workload Identities Premium (Conditional Access for workloads, risk detection, lifecycle reviews), credential hygiene (no client secrets where federation works), least-privilege RBAC, and integration with Defender for Cloud / Microsoft Entra Permissions Management. WHEN: managed identity, system-assigned identity, user-assigned identity, service principal hardening, workload identity federation, GitHub OIDC to Azure, Azure DevOps OIDC, AKS workload identity, kill client secrets, federated credential, Workload Identities Premium, Conditional Access for workloads, non-human identity governance, NHI, app registration hardening. DO NOT USE for user/human identity (use entra-id), permissions discovery across clouds (use entra-permissions-management), or end-to-end NHI governance (use agent-identity-governance).
This skill should be used when the user asks to "test for directory traversal", "exploit path traversal vulnerabilities", "read arbitrary files through web applications", "find LFI vulnerabilities", or "access files outside web root". It provides comprehensive file path traversal attack and testing methodologies
GCP cloud environment attack methodology. Use when the target uses Google Cloud Platform or when GCP Service Account/Metadata/Storage Bucket is discovered. Covers Metadata service exploitation, Service Account key theft, IAM privilege escalation, GKE escape, and Storage Bucket enumeration.
Use when adding authentication to a project scaffolded with genesis — login, sessions, SSO, admin users. Asks for an auth tier (basic/standard/strict), derives the mechanism from requirements, and implements it in place following the project's existing conventions.
Use GitHacker to exploit .git directory disclosure and recover the target's source code. GitHacker is a multi-threaded .git disclosure exploitation tool that, unlike git-dumper/GitHack, can recover more complete content — including stash, all branches, tags, and reflog. Even if the target disables directory listing (403), it can recover branches and tags through brute-force enumeration. Use this skill when the target's /.git/HEAD or /.git/config returns 200, when a .git/ directory is found in directory listings, or when version-control-related files are found during reconnaissance. After recovering the source code, you can look for hardcoded credentials, API keys, and database connection strings.
Interactive setup guide for using Infisical as a secret management tool in your projects. Helps users integrate Infisical into local development (CLI), Docker containers (build-time and runtime secret injection), CI/CD pipelines (GitHub Actions, GitLab CI), Kubernetes (Operator + CRDs), and application code (all 9 SDKs: Node.js, Python, Go, Java, .NET, Ruby, PHP, Rust, C++). Also walks through choosing and configuring any of the 13 machine identity auth methods (Universal, Token, Kubernetes, GCP, AliCloud, AWS, Azure, TLS Cert, OCI, OIDC, JWT, LDAP, SPIFFE). Use this skill whenever someone asks about: using Infisical, injecting secrets, infisical run, infisical init, connecting their app to Infisical, Docker secrets, Kubernetes secrets operator, machine identity setup, SDK initialization, CI/CD secret injection, or 'how do I get my secrets into my app'. Not for the Kubernetes Operator CRDs (infisical-kubernetes-operator), rendering secrets to files (infisical-agent), pushing secrets outward (infisical-secret-syncs), or human SSO login (infisical-sso).
Run an ISO 27001 internal audit. Walk through controls by domain, identify gaps, collect evidence, and generate findings with corrective action recommendations. Uses NIST SP 800-53 (public domain) as canonical reference. Use when user says "run internal audit," "ISO 27001 audit," "control assessment," "audit findings," or "ISMS assessment."
Kubernetes container escape and cluster attacks. Use when the target runs in a K8s environment, when ports 6443/10250/2379 are discovered, when a ServiceAccount Token is obtained, or when you are already inside a container. Covers container escape, Pod privilege escalation, API Server unauthorized access, etcd leakage, RBAC abuse, and node takeover. This skill should be used in any scenario involving Kubernetes, container orchestration, or cloud-native security.
Kubernetes storage and file share exploitation. Use when a Pod mounts NFS/EFS/PV/ConfigMap/Secret, when /efs or /mnt directories are found, or when a remote file system appears in mount output. Covers NFS mount exploitation, AWS EFS uid/gid spoofing, mountless reading with nfs-cat, and sensitive data extraction from PVs. Use this skill whenever any remote mount or shared storage is found in a container.
Receive and verify Klaviyo webhooks. Use when setting up Klaviyo webhook handlers, debugging Klaviyo-Signature verification, or handling Klaviyo system webhook events like event:klaviyo.opened_email, event:klaviyo.clicked_email, event:klaviyo.received_sms, or event:klaviyo.unsubscribed_from_email_marketing.
Detect, analyze, and remediate OWASP A10:2025 — Mishandling of Exceptional Conditions in Python web applications (FastAPI and Flask). Use this skill whenever the user asks about error handling security, exception management, fail-open vulnerabilities, stack trace exposure, uncaught exceptions, transaction rollback safety, or resource leaks in exception paths. Also trigger for any OWASP A10 audit, security code review involving try/except blocks, global exception handlers, or HTTP error responses that may leak sensitive information. If the user mentions CWE-209, CWE-248, CWE-636, CWE-703, CWE-754, or CWE-476 in a Python context, use this skill immediately.
Metasploit Framework usage methodology (one-liner + interactive). Use when exploiting OS-level vulnerabilities (such as EternalBlue/MS17-010), remote database vulnerabilities (such as PostgreSQL/MySQL RCE), or network service vulnerabilities (SMB/RDP/FTP), when a payload needs to be generated, when a reverse shell handler needs to be started, or for post-exploitation operations. MSF has 2000+ exploit modules covering remote exploitation of Windows/Linux operating systems, databases, and network devices. This skill also covers one-liner quick exploitation and interactive_session interactive operation (handler/meterpreter/post-exploitation). This skill should be used in any scenario involving metasploit, msfconsole, meterpreter, OS-level exploits, remote buffer overflows, payload generation, handlers, or post-exploitation.
Receive and verify Okta Event Hooks. Use when setting up Okta event hook handlers, implementing the one-time verification challenge, authenticating requests with the Authorization header secret, or handling identity events like user.lifecycle.create, user.session.start, user.account.lock, or group.user_membership.add.
Conduct authorized physical penetration testing against facilities, server rooms, and restricted areas using tailgating, RFID badge cloning, lock bypassing, rogue network device deployment, and security-guard procedure testing. Use as part of a full-scope red team engagement to evaluate physical security controls and their path to network access, always under signed client authorization.
Classifies text with Meta's Prompt Guard, an 86M-parameter model loaded from HuggingFace, into BENIGN, INJECTION or JAILBREAK labels to detect prompt injections and jailbreak attempts in LLM applications. Covers user input filtering, third-party data and RAG document filtering, batch processing, threshold tuning, and sliding-window handling of texts over 512 tokens. Use when screening user prompts for jailbreaks before they reach an LLM. Use when filtering API responses or retrieved RAG documents for embedded instructions. Use when batch-scanning documents for injection. Use when tuning detection thresholds or false positives on security-related queries. Use when running a lightweight CPU or GPU classifier for 8 languages. Not for content moderation such as violence or hate; use LlamaGuard for that.
Indirect prompt injection attacks against AI/LLM. Use when the target AI system processes external data sources (web pages, documents, emails, databases, API responses). Covers techniques such as indirect injection, tool chain hijacking, RAG poisoning and data exfiltration. The #1 vulnerability category in the OWASP LLM Top 10
Techniques for leaking AI/LLM system prompts. Use when the target is an LLM-based application and you want to obtain its system prompt, configuration information, tool list or knowledge base contents. A key first step for AI Bug Bounty, red team assessments and competitive analysis
Authors GitHub Actions quality-gate workflows for a Python repo — lint/type/test jobs, version matrices, uv caching, an all-checks-passed aggregator, required checks, rulesets, merge queues, SHA pinning, zizmor hardening. Use for 'set up continuous integration quality gates', 'make checks required', 'move branch protection to rulesets', 'harden the workflows'. Not for release pipelines or commit hooks.
QMEDR EDR telemetry threat hunting: after the runtime metadata explicitly exposes hunt, view the Doris/OCSF schema and run read-only SQL with a UTC time window and LIMIT, supporting searches by EID, event UID, process command line, file or network clues. Does not cover investigations of Endpoint/Signal/Incident operational objects, policy management, general database administration or general SQL development.
QMEDR policy domain queries: after confirming the current server metadata's describe result, read the policy audience and policy feature-flag, and handle detection, collection or policy write operations only when explicitly provided at runtime. Does not cover Endpoint/Signal/Incident investigation, telemetry SQL hunting, gray-release tasks or crash operations.
QMEDR security operations investigation: query managed hosts/Endpoints, EIDs, detection Signals, threat Incidents and the security posture Overview, completing filtering, statistics, details and evidence correlation, and answering the total number of gray-release machines, the cloud engine/endpoint engine ratio and the log reporting mode. Use when the user explicitly discusses QMEDR/EDR, gray-release machines, endpoint log reporting or detection engine modes, alert triage, threat investigation, incident UUIDs, signal UUIDs or endpoint EIDs; ordinary shell/command-line “terminal” and calendar/business “events” do not trigger it. Does not cover telemetry SQL hunting, policy management or devops gray-release task/crash operations diagnostics.
Shared rules and capability entry point for qmedr-cli: answers what qmedr can do and how to get started, and handles Taihu authentication, environment selection, dynamic metadata capability discovery, machine output and exit codes, readonly/operate, dry-run/--apply, RBAC, credentials and untrusted data. Use when the user asks about qmedr capabilities, post-install getting-started steps, login, configuration, missing commands, permissions or execution contracts; specific security operations, SQL hunting, policy and devops tasks go to their respective business Skills.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.