Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection signature detection, and adversarial robustness scoring.
184mo agoReviewMountCreate a free account to mount
Audit SkiaSharp's native dependencies for security vulnerabilities and CVEs, including Component Governance (CG) alerts from the combined skiasharp-package Azure DevOps pipeline. Read-only investigation that produces a status report with recommendations.
Review Langfuse changes for SSRF, tenant isolation, secret handling, unsafe redirects or uploads, RBAC drift, and client telemetry privacy. Use when a design or change accepts URLs or host fields, handles secrets or cross-tenant data, makes outbound requests, adds an integration, follows redirects, widens permissions, or can send customer-controlled UI data through analytics, monitoring, or session replay.
Use this skill for security standards at your managed IT services (MSP) business, in both directions: the baseline every managed client must meet (MFA, endpoint protection, email security, backups, admin access, offboarding) and how the MSP secures itself (RMM hardening, the credential vault, admin separation, partner-delegated admin access into client tenants, our own devices). Trigger on "security baseline", "security standard", "harden this tenant", "is this client secure enough", "security assessment", "cyber insurance questionnaire", "can we say we're compliant", HIPAA, FTC Safeguards, WISP, CMMC, PCI, CIS Controls, "lock down our RMM", or any question about what controls a client or our MSP should have. msp-helpdesk owns incident response; msp-maintenance owns patch and backup cadence; this skill owns the standard they deliver against. Apply alongside msp-onboarding, msp-qbr, msp-legal, msp-pricing, msp-client-comms, and msp-sales.
12115d agoReviewMountCreate a free account to mount
Triage a reported security finding into a disposition: a private CVE (coordinated disclosure + advisory), a public hardening PR (fix in the open, no CVE), or not-a-security-issue (reply to reporter). Assigns severity and affected maintained branches, and routes to the next step. Use when the user says "does this need a CVE", "CVE or hardening", "triage this report", "is this a security issue", "classify this finding", or "how should we disclose this".
31k18d agoReviewMountCreate a free account to mount
Router skill for API penetration testing across REST, GraphQL, gRPC, and WebSocket. Covers OWASP API Top 10 (2023) including BOLA/BFLA/BOPLA, JWT attack chains, GraphQL introspection abuse, and mass assignment. Invoke when the user asks to pentest an API, analyze OpenAPI/Swagger, test auth/authorization, fuzz endpoints, or find API vulnerabilities.
LLM and AI application security testing skill for prompt injection (direct, indirect, multimodal), system-prompt extraction, RAG poisoning, memory poisoning, MCP server injection, skill-file injection, agentic tool misuse, computer-use UI injection, and excessive agency. Authorization required — this skill tests AI systems you are explicitly permitted to assess. Triggers on requests to test LLM / AI-agent / RAG / MCP / computer-use security, perform prompt injection, extract system prompts, poison RAG or memory, audit agent tool use, or evaluate AI guardrails.
Security and compliance guidance for Amazon ECS — "ECS was unable to assume the role", task role vs execution role, iam:PassRole, confused-deputy aws:SourceArn trust, Fargate vs EC2 shared responsibility, injecting Secrets Manager/SSM secrets (trailing-colon JSON-key gotcha), readonlyRootFilesystem / non-root / drop capabilities, ECS Exec governance, security-group-per-task, VPC endpoint policies, GuardDuty ECS Runtime Monitoring, ECR Inspector scanning, image signing, Fargate FIPS, or PCI/HIPAA/FedRAMP. Walks a discovery-driven 7-layer stack plus the AWS-canonical baseline and a 30/60/90 roadmap. Trigger even if "compliance" is never said — any ECS hardening, task-trust fix, or secrets-injection qualifies. Skip for EKS/Kubernetes (eks-security), GenAI/GPU security (ecs-genai), App Runner/Lambda, auditing a live estate's operational posture (ecs-operation-review — "audit my ECS security posture" matches both), or account-level security with no ECS angle.
Read-only scripted security reviews of a live Amazon EKS cluster (exposed / not exposed / unknown), plus hardening and compliance guidance. (1) CVE and advisory review - "am I exposed to CVE-...", "check this AWS bulletin or GHSA against my cluster", "CVE review for EKS" - verdicts for add-ons and images; kubelet and node-OS items are review-only. (2) Security event response - compromised image or package, leaked credential, suspicious pod - scope, record, contain, snapshot, fix, verify. (3) Posture check - "would my cluster contain a compromised pod", IMDS, NetworkPolicy, PSA, identity, logging, GuardDuty, endpoint, supply chain. Also hardening and audit prep - 7-layer stack, CIS, HIPAA/PCI-DSS/FedRAMP/SOC 2, Pod Identity vs IRSA, Access Entries, image signing. Skip for EKS knowledge (eks-best-practices), Well-Architected review (eks-well-architected-review), upgrade readiness (eks-upgrade-check), an operational review (eks-operation-review), inventory (eks-recon), GenAI model security (eks-genai), non-EKS.
Harden Angular applications against common web vulnerabilities. Use when reviewing or improving app security, preventing XSS, configuring Content Security Policy (CSP) or Trusted Types, working with sanitization / DomSanitizer / bypassSecurityTrust, securing HttpClient (XSRF/CSRF, XSSI), auth and token storage, SSR/SSRF (allowedHosts), or keeping dependencies patched.
1344d agoReviewMountCreate a free account to mount
Use when auditing or hardening a Meteor 3 application. Triggers on missing check() on method arguments, missing this.userId guards on publications, browser-policy CSP, DDPRateLimiter rules, oauth-encryption via Accounts.config oauthSecretKey, audit-argument-checks, allow/deny legacy patterns, BrowserPolicy.content.disallowInlineScripts, BrowserPolicy.framing.disallow. Use this skill when the user asks about hardening, asks about a security review, or asks about CSP for a third-party script (Stripe, Google Maps, fonts).
21k2d agoReviewMountCreate a free account to mount
Audit CI/CD pipelines, GitHub Actions first and GitLab CI and CircleCI briefly, for the paths that give an outsider code execution, secrets or a write token: pull_request_target and workflow_run running untrusted code, expression injection into run steps, missing or broad workflow permissions, third-party actions not pinned to a commit SHA, OIDC trust policies with wildcard subjects, self-hosted runners on public repos, secrets reaching forks, cache and artifact trust between workflows, and AI agents in CI that read issue or PR text while holding a write token. Runs zizmor and actionlint read-only and writes findings.json. Use when the user mentions 'pull_request_target,' 'pwn request,' 'workflow injection,' 'zizmor,' 'actionlint,' 'pin actions to SHA,' 'GITHUB_TOKEN permissions,' 'self-hosted runner,' 'claude-code-action,' 'AI agent in CI,' 'GitLab CI security,' 'CircleCI security,' 'is this workflow safe,' or needs to secure a build pipeline.
48920d agoReviewMountCreate a free account to mount
Start here when a security ask is vague and no specific skill fits yet. Asks two or three questions about what you have (source code, a live site, a cloud setup, logs, a suspicious file, an auditor's request) and what's going on (building, shipping, an active incident, a compliance deadline), then hands off to the right skill or skills from this catalog, in order. It does no auditing itself. Use when the user says things like 'make this secure,' 'is this secure,' 'where do I start with security,' 'which security skill should I use,' 'security checkup,' 'what do we check,' 'secure my startup,' or 'help me with security' without naming a framework, a target or a tool. If the ask already names one (OWASP, a CVE, a workflow file, SOC 2, a phishing email, a pasted finding), use that skill directly instead.
48920d agoReviewMountCreate a free account to mount
Use when reviewing code security, auditing dependencies for CVEs, checking configuration or secret security, assessing authentication and authorization patterns, identifying OWASP vulnerabilities (injection, XSS, CSRF), or addressing security concerns about implementations.
Run OpenAlgo's periodic security audit across backend, frontend, database, cache, routes and dependencies, producing a dated xlsx report. Use for the monthly or twice-monthly review, before a release, after a dependency bump, or when the user asks for a security check, vulnerability scan, or audit report.
Audit commits that haven't been deployed yet for security vulnerabilities. Use when the user asks for a security audit, a pre-deploy security check, or to review undeployed commits for vulnerabilities.
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
Full security-audit orchestrator running /security-review, /cryptography-review, /threat-model, and /standards-review in canonical order per .github/skills/shared/orchestrator-contract.md. Each phase is a sub-agent (contract §6). Use before release or major changes; incremental skips only when explicitly requested for follow-ups.
3786d agoReviewMountCreate a free account to mount
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.