Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Security
Author an IndyKite ContX IQ (CIQ) policy plus its Knowledge Query that creates a brand-new relationship between two existing nodes in the IndyKite Graph (IKG), then run it via `POST /contx-iq/v1/execute`. Use when wiring two existing entities together through CIQ - no new nodes, no relationship updates, no deletes.
Methodology for using the Nuclei vulnerability scanner. Use when scanning targets for known vulnerabilities, verifying CVEs, or running batch PoC detection. Nuclei has 9000+ community-maintained templates covering CVEs, default credentials, misconfigurations, information leaks and more. This skill should be used for any scenario involving nuclei scanning, batch CVE verification, PoC detection, or vulnerability template search. It also applies when you need to extract payloads from nuclei templates for manual exploitation
Offline cyber security agent for the user's own apps and AI coding tools, run locally with the Penthera CLI; open R&D, measured in public. Sets it up in one command ("set up penthera in this repo"). Scans the user's own live URL and repo (TLS, headers, auth, OpenAPI, secrets incl. AI keys, opt-in injection); checks npm and Python dependencies offline ("is this dependency safe?", "what changed in my deps?", "install X safely", "any AGPL in our deps?"); blocks secrets and risky agent config before commit ("add a pre-commit hook"); audits AI tooling ("audit my MCP servers / skills / hooks", "check this skill before I install it"); fixes findings on a local branch and re-scans to verify ("scan and fix my app"); writes reports and evidence ("report for my auditor / manager", NIS2, SARIF, baseline diff). Use when the user asks to scan, audit, harden, fix, or review the security of their own app, staging URL, localhost, repo, dependencies, or agent setup. Do NOT use for targets without explicit authorization.
Residual re-identification RISK CHECK on text you have ALREADY redacted (defensive, dual-use). Use when the user asks to "check residual re-id risk", "red-team my redaction", "what can an attacker still infer", "is this safe to share", or assess "re-identification risk" after anonymizing. Re-runs the CONFIDE detectors on the redacted output to surface surviving identifiers (singling-out), checks multiple files for linkability, and optionally probes a local model for still-inferable attribute CATEGORIES (inference) — mapped to GDPR Art-29. Reports risk categories/counts only, never a re-identification recipe. Pairs with confide:anon (run AFTER redacting).
Use when reverse-engineering a binary or firmware — static triage + decompilation (Ghidra/IDA/Binary Ninja), dynamic instrumentation (GDB/Frida 17/angr), anti-reversing & packer bypass, OLLVM/VM deobfuscation, UEFI/BIOS RE & Secure Boot research, patch-diffing for n-days
Detect hardcoded sensitive data (API keys, access tokens, private keys, passwords, etc.) in publicly accessible code — frontend JavaScript, mobile apps, client-side bundles, and HTML templates. Uses a three-phase approach: recon (find secret candidates), batched verify (confirm real secrets in public code paths, 3 candidates each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/hardcodedsecrets-results.md. Use when asked to find hardcoded secrets, leaked API keys, or exposed credentials.
Detect insecure JWT (JSON Web Token) implementations in a codebase using a two-phase approach: first map all JWT issuance and verification sites to understand the token lifecycle and signing configuration, then check each verification site for exploitable weaknesses such as algorithm confusion, missing signature verification, weak secrets, header injection, and missing claim validation. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/jwt-results.md. If no JWT usage is found in Phase 1, Phase 2 is skipped. Use when asked to find JWT, token forgery, or authentication bypass bugs.
Run OWASP LLM Top 10 security assessments against live Agentforce agents. TRIGGER when: user asks for security testing, OWASP scan, red-teaming, penetration testing, security grade, vulnerability assessment, prompt injection test, data leakage test, excessive agency test, security posture check, or hardening recommendations. DO NOT TRIGGER when: user runs functional smoke tests or batch tests (use testing-agentforce); performs static safety review of .agent file content (use developing-agentforce Section 15); analyzes production session traces (use observing-agentforce); writes or modifies .agent files.
Set up, install, and configure CONFIDE local de-identification — installs Python deps (natasha, scrubadub, phonenumbers, pymorphy2), ensures Ollama + pulls the default qwen2.5:3b model, detects optional llama.cpp, and writes the optimal-default config so confide:anon and confide:red work with zero further config. Everything is local-first; raw text never leaves the machine. Use when the user says "set up confide", "install confide", "configure confide de-id", "confide setup", or "get confide ready".
Expert SOX IT General Controls (ITGC) advisor for finance, internal audit and IT compliance teams. Covers the four ITGC domains external auditors test for SOX 404 — access to programs and data, program changes, computer operations, and program development — plus scoping in-scope systems from the financial statements, designing risk-and-control matrices (RCMs), writing control narratives and test scripts, evaluating deficiencies (control deficiency vs significant deficiency vs material weakness under AS 2201 and Reg S-X), drafting remediation plans, SOX 404(a)/404(b) applicability and filer status, IPO readiness timelines, and COSO 2013 alignment. Use this skill whenever a user mentions SOX, ITGC, IT general controls, 404(a)/404(b), ICFR, material weakness, user access reviews, segregation of duties in IT, change management controls for financial systems, SOX testing or walkthroughs, PCAOB audits, or quarterly compliance for financial reporting systems.
Run a corpus-scale, STATS-ONLY PII audit over a folder of session transcripts LOCALLY and produce an aggregate report — counts by type and by layer, the per-session redaction-rate distribution, document lengths, and a coarse residual proxy. Use when the user says "audit my sessions", "scan folder for PII", "how much PII across these transcripts", "PII stats for my corpus", "is my redaction holding at scale", or points at a directory of transcripts and asks how much personal data it contains. Fully local — raw text never leaves the machine; the report carries ZERO PII values, transcript substrings, or filenames (only anonymized own-NN ids and counts), so the aggregates are safe to surface. Run it on a RED (raw) corpus to size the PII, or on a GREEN (already-redacted) corpus to check residual leakage.
Provides AWS CloudFormation patterns for IAM roles, policies, managed policies, permission boundaries, and trust relationships. Use when modeling least-privilege access, cross-account assumptions, service roles, or reusable IAM stacks that other CloudFormation templates consume.
Expert knowledge for Azure AI Face development including troubleshooting, best practices, decision making, limits & quotas, security, and integrations & coding patterns. Use when using Face detection, identification, verification, liveness, PersonGroup/Directory, or Face API quotas, and other Azure AI Face related development tasks. Not for Azure AI Vision (use azure-ai-vision), Azure AI Custom Vision (use azure-custom-vision), Azure AI Video Indexer (use azure-video-indexer), Azure AI Document Intelligence (use azure-document-intelligence).
Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables. Use when users mention Better Auth, betterauth, auth.ts, or need to set up TypeScript authentication with email/password, OAuth, or plugin configuration.
Ultimate AI-powered cybersecurity code review skill. Performs comprehensive security audit across 8 dimensions: vulnerability detection (OWASP Top 10:2021, CWE Top 25:2024), secret scanning, dependency/supply chain analysis, IaC security, threat intelligence (malware/backdoor/C2 detection, MITRE ATT&CK mapping), authorization verification, AI-generated code audit, and compliance mapping. Spawns 8 parallel specialist agents with weighted scoring (0-100). Framework-aware false-positive suppression. STRIDE threat modeling. Complements GitHub Advanced Security. Use when user says "security audit", "security review", "cybersecurity", "check for vulnerabilities", "OWASP check", "secure this code", "find security issues", "pentest review", "threat model", "security scan", "check security", "vulnerability scan", "code security", "appsec review", "supply chain check", "secret scan", "hardcoded credentials".
Convert text with private context or internal dependencies into generic, unbiased expressions that are standalone and reusable. Core goal — produce decontextualized text that preserves logic while removing organizational identifiers. Use for project handoff, open-source prep, methodology abstraction, cross-team sharing.
Detect Kerberos Pass-the-Ticket (PtT) attacks by analyzing Windows Event IDs 4768, 4769, and 4771 for anomalous ticket usage patterns, with detection queries for Splunk and Elastic SIEM. Use when investigating incidents involving stolen or replayed Kerberos tickets, building detection rules or threat hunting queries for ticket abuse, or validating SOC monitoring coverage for credential-theft attack techniques.
Runs a hypothesis-driven threat hunt for supply-chain compromise (T1195) by querying SIEM/EDR logs for trojanized software updates, compromised dependencies, unauthorized code modifications, and tampered build artifacts. Use when hunting after threat intel flags a compromised vendor/dependency, scoping a build-pipeline compromise, or reviewing update/build integrity.
Secures SaaS apps (Microsoft 365, Google Workspace, Salesforce, Slack) via CASB/SSPM deployment, conditional access policies, OAuth app governance, and session-level DLP controls enforcing identity verification and device compliance. Use when adding MFA/device-compliance conditional access, discovering shadow IT, governing OAuth consent grants, or applying session controls to sensitive SaaS data.
Author an IndyKite ContX IQ (CIQ) policy plus its Knowledge Query that sets one or more properties on an existing node in the IndyKite Graph (IKG), then run it via `POST /contx-iq/v1/execute`. Use when adding a brand-new property, overwriting an existing one, or attaching property metadata - no node creation, no relationship writes, no deletes.
Author an IndyKite ContX IQ (CIQ) policy plus its Knowledge Query that creates a brand-new node AND links it to one or more existing nodes via new relationships in a single `POST /contx-iq/v1/execute` call. Use when ingesting a new entity that must be wired into the IKG atomically — combines node creation and relationship creation in one operation.
Author an IndyKite ContX IQ (CIQ) policy plus its Knowledge Query that deletes a node, a relationship, or one or more properties from the IndyKite Graph (IKG), then run it via `POST /contx-iq/v1/execute`. Use when removing data through CIQ — three modes (whole node, whole relationship, individual property) sharing the same policy/KQ shape.
Design, implement, review, migrate, and troubleshoot secure JazzCash merchant payment integrations for Pakistani websites, apps, and commerce platforms. Cover HTTP POST redirection, approved APIs or hosted checkout, JazzCash Mobile Wallet, voucher payments, cards when enabled, secure hashes, callbacks, status checks, refunds, settlement, reconciliation, onboarding, testing, and production rollout. Use when adding JazzCash, repairing an existing JazzCash gateway, or upgrading an outdated merchant integration.
Comprehensive reference for LINE Login (OAuth 2.1) — authorization code flow, PKCE, token management, ID token JWT verification, user profiles, bot linking, and login button design. This skill should be used when the user asks to "implement LINE Login", "add Log in with LINE", "set up OAuth authorization flow", "verify an ID token", "refresh an access token", "link a bot to login", "design a login button", or mentions LINE Login, OAuth 2.1, PKCE, authorization code flow, ID token JWT verification, token refresh/revocation, user profile retrieval, bot linking, SSO login, LIFF authentication, or LINE MINI App authentication. Always use this skill whenever the user mentions LINE authentication, social login with LINE, or OAuth flows involving LINE, even if they don't explicitly say "LINE Login".
Turns kube-bench output into a finished CIS Kubernetes Benchmark audit: interpreting PASS/FAIL/WARN per control, judging which failures are genuine on a managed cluster, writing remediation, and packaging evidence for SOC 2 or PCI DSS. Use when conducting a scheduled compliance audit, triaging kube-bench results, deciding which controls are not applicable on EKS, GKE, or AKS, or producing hardening evidence for an auditor. Keywords: CIS Kubernetes Benchmark, control plane, remediation, compliance evidence, SOC 2, PCI DSS, managed cluster exception. Do not use for installing and running the tool - use benchmarking-kubernetes-with-kube-bench.
Put the real values back into an analysis that was produced from GREEN (placeholder) text — LOCALLY, using the user's own reversible map. Completes the confide round-trip (redact -> cloud-analyze the green -> rehydrate locally). Use when the user says "rehydrate", "restore real names", "unmask the analysis", "put the names back", "de-redact this output", "reverse the placeholders", or hands you an analysis full of [CONFIDE_PERSON_0001]/[CONFIDE_DATE_0002] plus a *.map.json. Runs only on the user's own map; the map never leaves the machine; nothing fetched or transmitted. Prints counts only — never echoes restored PII. Warns on placeholders not in the map (possible LLM hallucination).
Detect Server-Side Template Injection (SSTI) vulnerabilities in a codebase using a three-phase approach: recon (find template rendering sites that use dynamic strings), batched verify (trace user input to those sites in parallel subagents, 3 candidates each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/ssti-results.md. Use when asked to find SSTI or template injection bugs.
Web+AI security testing knowledge base. Combines 88,636 WooYun cases + Xianzhi L1-L4 methodology + GAARM 173 risks + OWASP Top 10 (LLM/ASI/WSTG). TRIGGER when the task is hands-on security testing: penetration testing, vulnerability discovery/exploitation, red team offense and defense, security auditing (SAST/DAST), CTF, AI/LLM security testing (prompt injection/jailbreak/MCP/Agent/sandbox escape). The user explicitly provides a test target (URL/code/model/Agent architecture) and the intent is "test/audit/find vulnerabilities/exploit". DO NOT trigger: - Security concept discussion ("what is XSS", "how does SQL injection work") → general Q&A - Non-security code review / debug / performance optimization → code-audit-skill or others - Fixing syntax errors / business logic bugs → general programming assistance - Pure web white-box code auditing (full project directory / Source-Sink taint analysis) → code-audit-skill - Looking up documentation by CVE number only → WebSearch - PI red team runs in Mira's built-in handbook / preview.mira.day (tier/TC-ID/resume) → mira-pi-tester - User wants to build/maintain their own markdown knowledge base/wiki ("knowledge base" here means the built-in read-only security corpus, not a user-editable wiki) → llm-wiki - Ingesting external PI/jailbreak articles into the Mira red team system (producing handbook TC cards) → mira-pi-ingest Boundary details: CTF short code snippet + exploitation idea → this Skill; full project directory + systematic white-box audit → code-audit-skill
Maintain Python packages through security audits or dependency updates using an isolated git worktree and uv. Use for security audits, CVE fixes, vulnerability checks, dependency updates, package upgrades, outdated packages, bump versions, fix Python vulnerabilities, check for Python CVEs, audit Python packages, update pyproject.toml dependencies, modernize Python deps, or when user types /uv-deps with or without specific package names or glob patterns.
Remediate GitHub Actions action findings identified by the action-audit skill. Applies the appropriate fix per action type — `@main` ref for internal `bitwarden/` actions, full SHA with inline version comment for external actions, or full replacement — across selected repos and creates draft PRs. Run the action-audit skill first to identify findings before using this skill. <example> User: Go ahead and fix the unpinned actions from the audit Action: Trigger action-remediate to apply fixes and create PRs </example> <example> User: Replace tj-actions/changed-files with the safe version across those repos Action: Trigger action-remediate to swap the action and create PRs </example>
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.