Security Skills

| Linux 内核 CVE 漏洞检测与 PoC 验证工具。88 个内核漏洞检测器，CTF 挑战模式验证。需要 root 权限（sudo）运行。 务必在检测内核漏洞时使用此技能。每当需要验证 CVE 或执行 PoC 验证时，优先调用此技能。 当用户提到内核安全、CVE 检测、漏洞利用验证时，主动触发。

> Linux 服务器安全入侵检测与取证工具，专为 AI Agent 设计。自动判断服务器是否被入侵， 提供完整证据链和可执行修复建议。50+ 安全分析器，10 个数据采集器，103+ MITRE ATT&CK 技术映射，支持 3 种部署模式。 当用户询问服务器安全、入侵检测、系统审计、恶意软件检测、安全事件响应时使用。 每当需要判断服务器是否被入侵、检查后门木马、分析安全事件时，优先使用此技能。 务必在发现安全异常时主动调用此技能，即使用户没有明确要求安全检查。

> Use when building ERPNext/Frappe API integrations (v14/v15/v16) including REST API, RPC API, authentication, webhooks, and rate limiting. Covers external API calls, endpoint design, token/OAuth2/session authentication. OAuth, frappe.call, external connection, rate limiting.

> Use when debugging or handling API errors in Frappe/ERPNext v14/v15/v16. Prevents silent failures and wrong HTTP status codes in REST endpoints. Covers 401 Unauthorized (wrong token format, expired OAuth), 403 Forbidden (missing @whitelist, allow_guest needed), 404 Not Found (wrong endpoint URL), 417 Expectation Failed (validation via frappe.throw), 500 Internal Server Error, CORS issues, CSRF token missing/invalid, rate limit exceeded (429), file upload failures, JSON parse errors in request/response, webhook delivery failures, and timeout on long operations. whitelist, webhook, rate limit, file upload, authentication token.

> Use when implementing OAuth providers, Connected Apps, Webhooks, Payment Gateways, or Data Import/Export in Frappe. Prevents authentication failures from wrong OAuth flow, missed webhook deliveries, and data corruption during bulk imports. Covers OAuth2 provider/client, Connected App DocType, Webhook DocType, Payment Gateway integration, Data Import, Data Export, frappe.integrations module.

> Use when configuring backups, restoring sites, encrypting backup files, scheduling automated backups, or planning disaster recovery. Prevents data loss from missing backups, failed restores, and unencrypted sensitive data. Covers bench backup, bench restore, backup encryption, S3/remote storage, scheduled backups, disaster recovery procedures.

> (1) User is new and hasn't run any tools yet, (3) Modal authentication errors occur, (4) User asks how to get started or set up the environment, (5) biomodals directory is missing or tools aren't working.

A Go security skill for reviewing code

> Use when the user wants an autonomous ML research loop that explores the space broadly rather than several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.

> Use when the user has a results draft or a set of data-backed claims and wants each one adversarially verified against the underlying dataset before publishing — a pre-publication red-team of the findings. Extracts the discrete checkable claims from the draft, reproduces each claim's number against the data, stress-tests it against the threats most likely to kill it (outliers, confounds, Simpson's reversals, tiny subgroups, alternative specifications), and marks it verified, fragile, or refuted; fragile and refuted claims are revised — hedged, scoped, or retracted — until every claim is verified or appropriately qualified. The result is a draft where every surviving claim has been reproduced and survived a stress test. Not for open-ended discovery of new findings over a dataset (that is a data-analysis task), and not for diagnosing a single known anomaly or pipeline failure — this is a gate over an existing draft.

Answer "who did what" security questions from Audit Trail — deletions, config changes, login activity, permission changes, actions from a specific user or IP.

Security forensics for git repos, AI skills, and MCP servers. Audits dependencies, detects prompt injection, credential theft, runtime dynamism, manifest drift, known CVEs, CISA KEV (actively exploited) vulns, and 2026 attack patterns. Not for fixing vulnerabilities or pentesting.

| 当系统提示需要防御提示注入、越狱攻击、社会工程、内容信任边界突破等安全威胁时调用此 Skill。适用于构建 AI Agent、聊天机器人、文档处理助手等任何接受外部输入的系统提示。不适用于纯内部工具调用场景或已完全隔离的沙箱环境，也不适用于 UI 布局或响应格式设计。

| 当需要为 AI 设计记忆存储、检索、应用和更新机制时调用此 skill。典型场景包括：设计持久化记忆架构（用户偏好、历史上下文、项目知识）、定义记忆的创建/读取/更新/删除生命周期、实现静默记忆应用（不在回复中透露记忆内容）、管理敏感记忆边界。 不适用于：定义工具接口（tool-specification）、定义安全规则（safety-guardrails）、定义人格风格（personality-system）。 关键 trigger 信号：AI 需要跨会话记住用户信息、记忆内容可能敏感、需要在回复中隐式应用记忆而非显式引用、用户要求"记住这个"。

| 当需要为 AI 系统设计多层安全防线、内容过滤策略和伦理边界时调用此 skill。典型场景包括：设计拒绝策略与升级机制、防御 prompt 注入攻击、实现领域特定安全规则（教育、医疗、金融等）、定义 AI 的价值观锚点。 不适用于：定义工具操作权限（应使用 tool-specification）、定义 AI 身份（persona-design）、调整输出风格（personality-system）。 关键 trigger 信号：AI 涉及敏感话题、需要设计"拒绝回答"策略、存在 prompt 注入风险、特定行业合规要求、需要多层防御而非单一规则。

| 当系统提示词需要为 AI 输出定义格式规范、长度约束、风格指南或反"AI味"策略时调用此 Skill。适用于聊天机器人、CLI 工具、移动端助手、设计生成器等需要自适应输出的场景。不适用于：纯内容生成（无格式要求）、内部推理链设计、安全策略制定。当需求仅涉及"用什么格式返回数据"而非"如何控制输出的风格与密度"时，这不是最佳 Skill。

| 当需要在基础身份之上叠加可切换的人格风格层时调用此 skill。典型场景包括：为同一产品提供多种人格选项（如 GPT-5.1 的 friendly/professional/quirky 模式）、设计人格切换机制、防止人格泄露到用户内容中。 不适用于：定义 AI 的核心角色定位（应使用 persona-design）、设计安全规则（应使用 safety-guardrails）。 关键 trigger 信号：产品需要多种语气风格、用户可切换 AI 性格、需要防止 AI 人格污染用户文本、存在 "personality" 或 "tone" 配置项。

Check email deliverability and DNS configuration. Use when: diagnosing email delivery issues; setting up new email domains; auditing email authentication; checking SPF/DKIM/DMARC; troubleshooting spam folder issues

Analyze your competitive landscape using Porter's Five Forces and modern frameworks—understand industry dynamics, identify strategic opportunities, and position your business for sustainable advantage. Use when: **Evaluate an industry** before entering or investing; **Understand competitive dynamics** in your market; **Identify strategic opportunities** based on industry structure; **Assess threats** from competitors, new entrants, or substitutes; **Develop positioning strategy** relative to ...

Connect WhatsApp to your product with Kapso: onboard customers with setup links, detect connections, receive events via webhooks, and send messages/templates/media. Also manage WhatsApp Flows (create/update/publish, data endpoints, encryption). Use when integrating WhatsApp end-to-end.

Use this skill when you need to design security testing around OWASP risks, vulnerability scanning, and penetration scenarios; triggers include security testing and vulnerability testing.

Use this skill when you need to design security testing around OWASP risks, vulnerability scanning, and penetration scenarios; triggers include 安全测试 and security testing.

Implement OAuth 2.0 authentication flows including authorization code with PKCE, client credentials, and device code for secure API integration.

Perform a comprehensive security audit of applications and infrastructure to identify vulnerabilities, assess risk, and recommend mitigations aligned with industry standards.

Conduct structured threat modeling for software systems using established methodologies to identify, prioritize, and mitigate security threats before they are exploited.

Design and review APIs with suggestions for endpoints, parameters, return types, and best practices. Use when designing new APIs from requirements, reviewing existing API designs, generating API documentation, or getting implementation guidance. Supports REST APIs with focus on endpoint structure, request/response schemas, authentication, pagination, filtering, versioning, and OpenAPI specifications. Triggers when users ask to design, review, document, or improve APIs.

Analyzes code to identify security-critical time intervals and timing vulnerabilities in authentication, authorization, and time-sensitive security operations. Use this skill when reviewing code for proper timeout enforcement, token expiration, session management, rate limiting, password reset validity, or any time-sensitive security mechanism. Detects missing expiration checks, excessive timeout values, lack of rate limiting, client-side only validation, hardcoded timeouts, and timing attack vulnerabilities. Triggers when users ask to check security timeouts, verify token expiration handling, audit session timeout implementation, review rate limiting, or analyze time-based security controls.

Analyze CVE reachability in software repositories by examining how vulnerable dependencies are imported and used. Determines whether vulnerable components, classes, or functions are reachable from project code through call chain analysis, reflection detection, dynamic loading patterns, and configuration-gated behavior. Classifies each CVE as likely reachable, possibly reachable, or likely unreachable with supporting evidence. Use when analyzing security vulnerabilities in dependencies, performing post-disclosure CVE triage, assessing vulnerability impact, or when users ask to analyze CVE reachability, check if vulnerabilities are exploitable, or evaluate dependency security risks.

Generate prioritized CVE watchlists and actionable security recommendations for repositories. Use when analyzing CVE scan results, creating security reports, prioritizing vulnerability remediation, or generating security gate reports for CI/CD. Takes CVE scan results (JSON/SARIF from npm audit, pip-audit, Snyk), reachability analysis, and cutoff date as input. Combines severity, reachability, exploitability, and dependency criticality to rank CVEs by practical risk. Outputs markdown reports with concrete next-step guidance (immediate upgrade, monitor, ignore with justification, apply mitigation) suitable for issue trackers, security reviews, and CI security gates.

Analyze detected vulnerabilities to assess realistic exploitability by examining control flow, input sources, sanitization logic, and execution context. Use when users need to: (1) Determine if a vulnerability is actually exploitable in practice, (2) Assess severity and impact of security issues, (3) Prioritize vulnerability remediation, (4) Understand attack vectors and exploitation conditions, (5) Generate exploitability reports with proof-of-concept scenarios. Focuses on injection vulnerabilities (SQL, command, XSS, path traversal, LDAP) with detailed analysis of reachability, controllability, sanitization, and impact.

Proposes secure remediation strategies for detected security vulnerabilities including buffer overflows, injection risks, insecure deserialization, improper authentication, and unsafe cryptographic usage. Provides recommended security checks, safer API alternatives, design-level changes, code examples, trade-off analysis, and prioritized remediation plans. Does NOT automatically modify code unless explicitly requested.

Instruments authentication, authorization, and input-handling code paths to monitor security-relevant events and states at runtime. Use this skill when developers need to add security monitoring and logging to their code, including tracking authentication attempts (login/logout), authorization decisions (access control checks), input validation failures, session management events, and other security-critical operations. Supports Python, JavaScript/TypeScript, and Java with structured logging patterns. Triggers when users ask to add security instrumentation, monitor security events, log authentication/authorization, track security-sensitive operations, or add security observability to their codebase.

Statically analyze code to detect security vulnerabilities including buffer overflows, injection risks (SQL, command, XSS), insecure deserialization, improper authentication, hard-coded credentials, and unsafe cryptography. Use when: (1) Performing security code review, (2) Analyzing code for OWASP Top 10 vulnerabilities, (3) Identifying CWE-classified weaknesses, (4) Generating security audit reports, (5) Reviewing code before deployment, or (6) Assessing third-party code security. Findings categorized by CWE ID and severity (Critical/High/Medium/Low).

Scan repositories for newly disclosed CVEs in dependencies after a specific cutoff date. Takes a repository path, cutoff date (YYYY-MM-DD), and optional parameters for transitive dependencies. Parses dependency manifests (package.json, pom.xml, requirements.txt, go.mod, Cargo.toml) and lockfiles to extract exact versions. Queries vulnerability databases (OSV.dev, NVD, GitHub Advisory) to identify CVEs disclosed strictly after the cutoff date. Distinguishes between newly disclosed CVEs and previously known CVEs. Use when: (1) Performing security audits to find new vulnerabilities since last review, (2) Checking if new CVEs affect a historical codebase version, (3) Generating compliance reports showing vulnerability status at specific dates, (4) Tracking security posture changes over time. Supports npm, Maven, pip, Go modules, Cargo, and other major ecosystems.

Detects security vulnerabilities by matching code against known vulnerability patterns, insecure coding idioms, and CVE-style patterns. Explains why patterns are risky and under what conditions they are exploitable. Use when analyzing code for security issues, reviewing for common vulnerabilities, or assessing exploitability of suspicious code patterns.

Analyze vulnerable code to identify underlying root causes such as violated assumptions, incorrect invariants, missing validation checks, or unsafe component interactions. Use when investigating security vulnerabilities, CVEs, exploit code, or security audit findings. Infers why the vulnerability exists beyond surface symptoms, identifies systemic issues, and explains the chain of failures that enable exploitation.

Optional, opt-in STRIDE threat pass for a sensitive feature — invoked deliberately via /threat-model, never forced on ordinary changes. Walks the change's attack surface and security boundaries (governed by {{PROJECT_DIR}}/.codearbiter/security-controls.md), surfaces threats and unmitigated gaps, and MAY dispatch security-reviewer or auth-crypto-reviewer. Not a routine gate; it can hard-STOP only on a genuinely critical unmitigated threat it surfaces.

Optional, opt-in STRIDE threat pass for a sensitive feature — invoked deliberately via /threat-model, never forced on ordinary changes. Walks the change's attack surface and security boundaries (governed by <project-root>/.codearbiter/security-controls.md), surfaces threats and unmitigated gaps, and MAY dispatch security-reviewer or auth-crypto-reviewer. Not a routine gate; it can hard-STOP only on a genuinely critical unmitigated threat it surfaces.

Opt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a change warrants security thought.

Optional, opt-in STRIDE threat pass for a sensitive feature — invoked deliberately via /threat-model, never forced on ordinary changes. Walks the change's attack surface and security boundaries (governed by <project-root>/.codearbiter/security-controls.md), surfaces threats and unmitigated gaps, and MAY dispatch security-reviewer or auth-crypto-reviewer. Not a routine gate; it can hard-STOP only on a genuinely critical unmitigated threat it surfaces.

Opt-in lightweight STRIDE pass for a sensitive feature before implementation. Not a routine gate — invoke it when a change warrants security thought.

Run Claude Code INSIDE a ca-sandbox box (`--with-claude`). Routed to when the user wants an agent loop running against an isolated, ephemeral sandbox rather than the host. Authenticates via an env-injected CLAUDE_CODE_OAUTH_TOKEN with no host bind of ~/.claude; the image pins the CLI and disables the autoupdater; HOME is backed by a named volume so the .claude state persists across restart. Five gated phases — posture, image, token, run, teardown. The hard default is offline or Anthropic-domains-only egress, and the token volume is NEVER co-mounted with an untrusted-code run; both are enforced, not advised.

Optional, opt-in STRIDE threat pass for a sensitive feature — invoked deliberately via /threat-model, never forced on ordinary changes. Walks the change's attack surface and security boundaries (governed by ${CLAUDE_PROJECT_DIR}/.codearbiter/security-controls.md), surfaces threats and unmitigated gaps, and MAY dispatch security-reviewer or auth-crypto-reviewer. Not a routine gate; it can hard-STOP only on a genuinely critical unmitigated threat it surfaces.

>- Apply the SAIL (Secure AI Lifecycle) V2 framework by Pillar Security to secure AI applications and agents. Use this skill whenever the user asks about AI or agent security — assessing an AI system or agent architecture for risks, building an AI security roadmap or maturity assessment, writing or reviewing an AI security policy, creating compliance checklists (ISO/IEC 42001, EU AI Act, OWASP LLM/Agentic, DASF, AIUC-1), prioritizing AI security controls, evaluating AI vendors or tools (RFPs, security questionnaires), securing MCP servers, agent identities, or LLM apps, or asking what "SAIL" or a "SAIL ID" (e.g., SAIL 5.17) means. Also use it when the user is building agentic features and wants to know which security risks apply — even if they never say "SAIL".

Self-contained SaaS automation — invoke directly, do not decompose. Transforms a Vibes app into a multi-tenant SaaS with subdomain-based tenancy. Adds Pocket ID authentication, subscription gating, and generates a unified app with landing page, tenant routing, and admin dashboard. Use when the user wants to monetize an app, add auth and billing, create a SaaS product, add subscriptions, or turn an app into a business.

> (1) User is new and hasn't run any tools yet, (3) Modal authentication errors occur, (4) User asks how to get started or set up the environment, (5) biomodals directory is missing or tools aren't working.

Search NCBI databases using Biopython Bio.Entrez (ESearch, EInfo, EGQuery, ESpell). Use when finding records by keyword, building reproducible field-qualified queries, navigating the Entrez Query Translator, exploiting the history server for large result sets, handling retmax caps, or interpreting weekly index lag. Covers PubMed, Nucleotide, Protein, Gene, SRA, GEO, Assembly, Taxonomy, ClinVar, dbSNP.

Tests genotype-environment associations and identifies loci under local adaptation using LFMM2 (LEA), pcadapt outlier detection, OutFLANK Fst-based selection scans, and redundancy analysis. Detects adaptive genetic variation correlated with environmental variables while controlling for population structure. Use when identifying adaptive loci across environmental gradients, testing for signatures of local adaptation, or predicting genetic vulnerability to climate change with gradientForest.