Claude Skills by aibot88

Use when implementing authentication/authorization, securing user input, or preventing OWASP Top 10 vulnerabilities — including custom security implementations such as hashing passwords with bcrypt/argon2, sanitizing SQL queries with parameterized statements, configuring CORS/CSP headers, validating input with Zod, and setting up JWT tokens. Invoke for authentication, authorization, input validation, encryption, OWASP Top 10 prevention, secure session management, and security hardening. For p...

Proactive secure-coding coach scoped to the file or topic you are working on — surfaces relevant SAST rule IDs, CWE patterns, language-specific PASS/FAIL code snippets. Use when about to write auth, crypto, SQL, deserialization, file-handling, or template code; coaching juniors; pair-programming a security-sensitive change.

Use when performing deep security review of auth, crypto, secrets, or PII code requiring confidence-rated severity findings and OWASP checks

Container, K8s, CI/CD ve runtime security review.

Define, build, review, and harden production-grade fullstack applications with strong security posture. Use this skill when the user wants to establish a project baseline, implement software, review frontend/browser-side vulnerabilities, or strengthen existing code and configuration. Produces practical engineering output, rigorous security thinking, and continuity-aware iterations that avoid security theater.

Generate secure microsoft word file validation code. Enforces secure generation of code validating a microsoft word file. Invoke when writing any microsoft word file validation related code. See "security-considerations" metadata for security limitations.

Retroactively verify threat mitigations for a completed phase

Use when writing or reviewing code that handles external input, manages access, touches data or crypto, or changes dependencies. Triggers: endpoints, auth/authz, DB/ORM, file handling, secrets, "is this secure?", "security review". NOT for formatting, pure UI, or explaining code.

Create and secure S3 buckets following AWS best practices for access control, encryption, monitoring, and remediation of misconfigurations. Use when the user wants to secure a new bucket, audit an existing bucket, fix a security finding, configure encryption, or enable logging and monitoring. Do NOT use for general S3 data operations, S3 Tables setup, or discovering existing data assets.

Règles essentielles de sécurité ANSSI pour le développement d'applications de l'État. 12 règles couvrant TLS, secrets, authentification, headers, dépendances, entrées, logs et durcissement. Utiliser cette skill quand l'utilisateur développe une application web, une API, ou tout service exposé, quand il mentionne la sécurité, l'ANSSI, le durcissement, ou quand on configure un serveur, un reverse proxy ou un pipeline CI/CD.

Scans email threads for security alert signals — phishing reports, suspicious login notifications, data breach mentions, policy violation flags, vulnerability disclosures, and any language suggesting a security incident may be developing. Use when an IT security team wants an early warning scan across their email communications. Triggers on "security alerts", "security incidents from email", "phishing reports", "suspicious activity", "security signal scan", "what security issues are brewing".

Evaluate security posture and regulatory compliance for a system architecture. Produces .forge/security.md with auth model, data isolation, PII inventory, regulatory requirements, encryption audit, vendor assessment, certification roadmap, and STRIDE threat model. Use when user mentions "security review", "compliance", "SOC 2", "GDPR", "PII", "threat model", or the system handles sensitive data.

Use when writing or reviewing code that parses user input, builds SQL/shell commands, handles secrets/credentials, hashes passwords, changes auth checks, deserializes untrusted data, or constructs paths/URLs from input

Durcissement de la sécurité des APIs — rate limiting, validation d'entrée, headers de sécurité, CORS, protection contre les attaques courantes. À utiliser quand l'utilisateur sécurise une API, configure des headers de sécurité ou implémente du rate limiting. Se déclenche aussi avec "sécurité API", "rate limiting", "headers sécurité", "CORS", "API hardening", "protection API", "OWASP API".

Security Architect: Security by Design fuer den gesamten Entwicklungsprozess. 4 Modi: DESIGN (Threat Modeling bei Ideation/Planung), REVIEW (Security-Check bei Code-Aenderungen), AUDIT (vollstaendiger Security-Scan auf Abruf), SKILL-SCAN (Prompt-Injection-Check fuer heruntergeladene Skills/SKILL.md-Dateien vor der Installation). Kombiniert STRIDE/DREAD Threat Modeling, OWASP Top 10:2025, ASVS 5.0, Agentic AI Security und konkrete Secure-Code-Patterns. Verwenden wenn der Nutzer "security", "si...

Execute STRIDE threat modeling, vulnerability scanning, and security control validation with risk scoring

引导安全审查和漏洞评估，遵循 OWASP 标准。 使用时机：安全审计、漏洞检查、安全编码审查、威胁建模。 关键字：security, OWASP, vulnerability, authentication, authorization, 安全, 漏洞, 认证。

Automatisation d'audits de sécurité incluant scanning, reporting, intégration CI/CD et remediation tracking. Se déclenche avec "audit automatisé", "security scanning", "SAST", "DAST", "Trivy", "Snyk", "audit CI/CD"

Security Audit Skill is built around OWASP security tooling ecosystem. The underlying ecosystem is represented by zaproxy/zaproxy (14,896+ GitHub stars). It gives an agent a more technical and reliable way to work with the tool than a thin one-line wrapper, using stable interfaces like ZAP scanning, passive/active checks, auth contexts, alerts, HTTP spidering and preserving […]

Security audit methodology and checklist for codebases. Use when performing security reviews, auditing a project for vulnerabilities, or hardening an application before deployment. Covers secret scanning, input validation, authentication/authorization, cryptographic practices, dependency auditing, CSP configuration, rate limiting, OWASP Top 10 checks, and audit report format. Derived from production audit work.

Specialista na autentizaci a autorizaci. MUSÍ být použit při analýze bezpečnosti kódu — hledá slabé hashování hesel (MD5/SHA1) a chybějící autorizační kontroly.

Teaches agents to recognize and avoid security threats during normal activity. Covers phishing detection, credential protection, domain verification, and social engineering defense. Use when building or operating agents that access email, credential vaults, web browsers, or sensitive data.

Базовая безопасность в реализации — валидация входных данных (Zod), secrets management, безопасные ошибки, auth/authz patterns, XSS/injection prevention, dependency audit, secure headers. DO/DON'T примеры. Активируй при написании любого кода, работающего с пользовательским вводом, auth, секретами, или при вопросах «как сделать безопасно».

Establish a security baseline for a website or web app. Use this skill when configuring HTTPS and TLS, setting security headers, planning secrets management, evaluating CSP policies, doing a basic security audit, or hardening a site before launch. Triggers on security headers, HTTPS, TLS, CSP, content security policy, HSTS, secrets management, vulnerability scan, security audit, harden, OWASP, security baseline. Also triggers when a security review is required for compliance or before going l...

中文优先：用于安全bountyhunter相关任务，帮助识别、设计、实现或验证对应工作流。English keywords: Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.

Comprehensive AI-powered security scanning suite with 48 skills covering OWASP Top 10, 7 language-specific deep scanners (Go, TypeScript, Python, PHP, Rust, Java, C#), supply chain analysis, infrastructure-as-code scanning, and 3000+ checklist items. Use when you need to run a security audit, find vulnerabilities, scan a PR for security issues, or perform a penetration test on a codebase.

OWASP-based security checklist any agent can reference when reviewing or writing code

Przegląd bezpieczeństwa zmian w kodzie i konfiguracji.

Vérification de conformité sécurité incluant ISO 27001, SOC 2, HIPAA, NIST et audit trail. Se déclenche avec "ISO 27001", "SOC 2", "HIPAA", "NIST", "conformité sécurité", "audit sécurité", "compliance"

Performs advanced SAST (Static Application Security Testing) and compliance analysis on Pull Request diffs. Identifies real security vulnerabilities, secrets, and regulatory compliance violations (GDPR, HIPAA, SOC2, PCI-DSS) by analyzing only changed code. Multi-language with exploitability assessment and CWE mapping.

Walk a security team member through allocating a CVE for an <tracker> tracking issue. Prints the ASF Vulnogram allocation URL and a CVE-ready title (the issue title stripped of redundant `<vendor>: <product>:` (e.g. `Apache Airflow:`), `[ Security Report ]`, trailing version parens and similar noise), waits for the allocated CVE ID (allocation is PMC-gated — non-PMC triagers relay to a PMC member), and then updates the tracker in place: fills in the *CVE tool link* field, adds the `cve alloca...

GitHub security alerts command center -- triage Dependabot, code scanning, and secret scanning alerts entirely from the editor. Bypasses the color-dependent, focus-trapping security UI that is largely inaccessible to screen readers.

Audit de sécurité des dépendances — détection de vulnérabilités connues, mises à jour critiques et gestion du cycle de vie des packages. À utiliser quand l'utilisateur veut vérifier la sécurité de ses dépendances, mettre à jour des packages vulnérables ou mettre en place un processus d'audit continu. Se déclenche aussi avec "audit dépendances", "vulnérabilité npm", "CVE", "dépendance vulnérable", "npm audit", "dotnet audit", "supply chain security", "dependabot".

Sempre considera vetores OWASP top-10 ao escrever/revisar código

Security remediation en vulnerability fix skill. Past fixes toe voor kwetsbaarheden uit security check-rapporten. Automatische dependency updates, configuratie-patches, code fixes via Edit tool, en PR-creatie. Gebruik na een security audit/scan om kritieke en hoge severity issues op te lossen.

Adversarial defense layer for the mortgage plugin — protects against prompt injection, system prompt extraction, PII leakage, workflow bypass, and social engineering attacks.

Sécurisation d'agents IA contre injections, abus et fuites de données. Se déclenche avec "sécurité agent", "agent security", "prompt injection", "jailbreak", "agent abuse", "guardrails", "safe agent", "sécuriser mon agent", "agent en production sécurisé".

Security headers and hardening for Next.js — CSP, CORS, rate limiting, CSRF protection, input sanitization, secrets management. Use when hardening a Next.js app, configuring security headers, or implementing rate limiting.

Security hygiene for GSD's self-modifying skill and agent system. Use this skill whenever: creating, editing, or deleting skill files (.claude/skills/, .claude/commands/), modifying agent definitions (.claude/agents/), working with YAML configuration or chipset files, handling JSONL observation data (.planning/patterns/), processing community-contributed skills or chipsets, any file path operations that could involve user input, or when installing/updating project-claude configuration. Also a...

Plan de réponse aux incidents de sécurité — préparation, détection, containment, éradication, recovery et lessons learned. Se déclenche avec "incident response", "plan de réponse", "breach", "compromission", "réponse à incident", "CSIRT".

Merge two <tracker> tracking issues that describe the same root-cause vulnerability (typically discovered independently by two reporters, arriving via different channels), preserving every reporter's credit, every mailing-list thread reference, and every independent attack-vector description. Updates the kept issue's body in place, closes the duplicate with the `duplicate` label, and regenerates the CVE JSON attachment so both finders land in `credits[]`.

Attempt to fix a security issue tracked in <tracker> by implementing the change in a public <upstream> PR. Runs the security-issue-sync skill first to reconcile the issue's state, then analyses the discussion to decide whether the issue is easily fixable (clear consensus, small scope, known location). If it is, proposes an implementation plan, waits for explicit user confirmation, writes the change in the user's local <upstream> clone, runs the local checks and tests, opens a PR from the user...

Open one or more `<tracker>` tracking issues from a markdown file containing a batch of security findings (typically the output of an AI security review or a third-party scanner). Each finding in the file becomes one tracker, landing in the `Needs triage` board column with the standard issue-template body fields populated from the markdown sections. Unlike `security-issue-import` (Gmail) and `security-issue-import-from-pr` (public PR), there is no inbound reporter to reply to and no PR to ins...

Open a tracking issue in <tracker> for a security-relevant fix that has already been opened (or merged) as a public PR in <upstream>, in the case where there is no inbound `<security-list>` report. The tracker lands in the `Assessed` board column (the team-deliberate import implies the security assessment has already happened) with the scope label applied, `pr created` / `pr merged` reflecting the PR's state, and `Remediation developer` / `PR with the fix` body fields populated from the PR — ...

Scan <security-list> for reports that have not yet been copied into <tracker> as tracking issues, present the proposed imports to the user, and — defaulting to *import unless the user rejects upfront* — create the tracking issues with the `Needs triage` project-board status and draft a receipt-of- confirmation reply to each reporter. This is the first step of the handling process: the entry point that converts an inbound email thread into a tracker the rest of the skills (security-issue-sync,...

Close an `<tracker>` tracking issue as invalid: apply the `invalid` label, remove the scope label, post a short closing comment, archive the item from the project board, and — for trackers imported from `<security-list>` — draft a polite-but-firm reply to the reporter on the original Gmail thread explaining the team's reasoning (extracted from the tracker's discussion). For trackers opened via `security-issue-import-from-pr`, the email-draft step is skipped per the *no outreach to the PR auth...

Synchronize a security issue in <tracker> with the state of its GitHub discussion, the <security-list> mailing thread, and any <upstream> PRs that fix it. The skill gathers all relevant signals, proposes label, milestone, assignee, field and draft-email updates, and only applies changes the user has explicitly confirmed. Suggests the next step in the handling process and prints the CVE allocation link when a CVE is needed.

For each open `<tracker>` issue carrying the `needs triage` label, read body + comments and classify the candidate disposition into one of five classes: VALID / DEFENSE-IN-DEPTH / INFO-ONLY / INVALID / PROBABLE-DUP. On user confirmation, posts a triage-proposal comment that invites the security team to react. Read-only on tracker state — no label flips, closes, or CVE allocations. Supports `--retriage` for re-litigating passed-triage decisions when substantive new activity lands.

Automate security monitoring, threat detection, incident response, and compliance workflows

Automated PII detection and redaction for client data protection. Scans outputs, logs, artifacts, and communications for sensitive data before external exposure. Derived from ruflo agent-security-manager + @claude-flow/aidefence patterns. Use when: generating client reports, sending emails, creating external documents, logging data. Skip when: internal-only analysis, no client data involved.