安全

安全审查、认证、权限和风险检查

608 个 Skills 可用

Skills 列表

dnanexus-integration

dnanexus-integration

42Ksecurity

Build and operate reproducible genomics workloads on DNAnexus with the dx CLI, dxpy, apps/applets, native workflows, dxCompiler, and Nextflow. Use for DNAnexus data transfers, dxapp.json development, execution monitoring, workflow import, and project automation.

k-dense-ai avatark-dense-ai
获取
transformers

transformers

41Ksecurity

Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and multimodal tasks. Use when working with AutoModel, pipelines, tokenizers, or TrainingArguments—not for general ML outside the Transformers library.

k-dense-ai avatark-dense-ai
获取
github-actions-hardening

github-actions-hardening

39Ksecurity

Security hardening reviewer for GitHub Actions workflow files (.github/workflows/*.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill when asked to review, audit, harden, or secure a GitHub Actions workflow, when writing a new workflow, or for any request like "is this workflow safe?", "review my CI for security issues", "why is pull_request_target dangerous here?", "pin my actions", or "lock down GITHUB_TOKEN permissions". Covers script injection via ${{ }} interpolation, pull_request_target / workflow_run privilege escalation, SHA-pinning of third-party actions, least-privilege permissions, GITHUB_ENV/GITHUB_OUTPUT injection, secret exposure, OIDC over long-lived credentials, and self-hosted runner exposure on public repositories.

github avatargithub
获取
arize-ai-provider-integration

arize-ai-provider-integration

39Ksecurity

Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports any LLM provider (e.g. OpenAI, Anthropic, Azure OpenAI, AWS Bedrock, Vertex AI, Gemini, NVIDIA NIM). Use when the user mentions AI integration, LLM provider credentials, create integration, list integrations, update credentials, delete integration, or connecting an LLM provider to Arize.

github avatargithub
获取
agent-owasp-compliance

agent-owasp-compliance

38Ksecurity

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"

github avatargithub
获取
quality-playbook

quality-playbook

38Ksecurity

Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.

github avatargithub
获取
exploratory-data-analysis

exploratory-data-analysis

38Ksecurity

对明确支持的科学文件执行有界、本地的探索性分析。用于脱敏的CSV/TSV/JSON配置文件;可选的NumPy、HDF5、FASTA/FASTQ和基本图像元数据检查;缺失性/泄漏审计;异常值和变换敏感性;以及严格的EDA报告框架。其他领域格式仅作参考,未知格式默认拒绝。

k-dense-ai avatark-dense-ai
获取
security-review

security-review

37Ksecurity

AI驱动的代码库安全扫描器,像安全研究员一样推理代码——追踪数据流、理解组件交互、捕捉模式匹配工具遗漏的漏洞。当被要求扫描代码安全漏洞、查找错误、检查SQL注入、XSS、命令注入、暴露的API密钥、硬编码密钥、不安全的依赖、访问控制问题,或任何类似“我的代码安全吗?”、“审查安全问题”、“审计此代码库”或“检查漏洞”的请求时,使用此技能。涵盖JavaScript、TypeScript、Python、Java、PHP、Go、Ruby和Rust中的注入缺陷、身份验证和访问控制错误、密钥暴露、弱加密、不安全的依赖以及业务逻辑问题。

github avatargithub
获取
copilot-spaces

copilot-spaces

37Ksecurity

使用 Copilot Spaces 为对话提供项目特定的上下文。当用户提到“Copilot space”、想要从共享知识库加载上下文、发现可用的空间,或提出基于精选项目文档、代码和指令的问题时,使用此技能。

github avatargithub
获取
peer-review

peer-review

37Ksecurity

Prepare evidence-bounded, constructive peer-review drafts and structured manuscript assessments. Use for authorized review of scientific manuscripts, protocols, preprints, or research proposals; reporting-guideline selection; claim–evidence checks; methods, statistics, reproducibility, ethics, figure/table, and citation critique; or revision-response planning.

k-dense-ai avatark-dense-ai
获取
msstore-cli

msstore-cli

37Ksecurity

Microsoft Store 开发者命令行工具(msstore),用于将 Windows 应用程序发布到 Microsoft Store。当需要配置商店凭据、查看商店应用列表、检查提交状态、发布应用提交、管理 package flight(测试分发包)、配置商店发布的 CI/CD 流水线或对接 Partner Center 时使用。支持 Windows App SDK/WinUI、UWP、.NET MAUI、Flutter、Electron、React Native 及 PWA 应用。

github avatargithub
获取
mcp-create-declarative-agent

mcp-create-declarative-agent

37Ksecurity

由 mcp-create-declarative-agent.prompt.md 转换而来的 Skill

github avatargithub
获取
dataverse-python-usecase-builder

dataverse-python-usecase-builder

37Ksecurity

为特定的 Dataverse SDK 用例生成完整解决方案,并附带架构建议

github avatargithub
获取
entra-agent-user

entra-agent-user

37Ksecurity

在 Microsoft Entra ID 中从代理标识创建代理用户,使 AI 代理能够作为数字工作者在 Microsoft 365 和 Azure 环境中使用用户身份功能。

github avatargithub
获取
git-flow-branch-creator

git-flow-branch-creator

36Ksecurity

智能 Git Flow 分支创建器,分析 git status/diff 并根据 nvie Git Flow 分支模型创建合适的分支。

github avatargithub
获取
architecture-blueprint-generator

architecture-blueprint-generator

36Ksecurity

全面的项目架构蓝图生成器,可分析代码库以创建详细的架构文档。自动检测技术栈和架构模式,生成可视化图表,记录实现模式,并提供可扩展的蓝图,以维护架构一致性并指导新开发。

github avatargithub
获取
apple-appstore-reviewer

apple-appstore-reviewer

36Ksecurity

作为代码库的审查者,负责查找Apple App Store优化或拒绝原因。

github avatargithub
获取
create-github-action-workflow-specification

create-github-action-workflow-specification

36Ksecurity

为现有的 GitHub Actions CI/CD 工作流创建正式规范,优化用于 AI 消费和工作流维护。

github avatargithub
获取
azure-devops-cli

azure-devops-cli

36Ksecurity

通过CLI管理Azure DevOps资源,包括项目、仓库、流水线、构建、拉取请求、工作项、制品和服务终结点。当使用Azure DevOps、az命令、devops自动化、CI/CD,或用户提及Azure DevOps CLI时使用。

github avatargithub
获取
scientific-writing

scientific-writing

34Ksecurity

Draft, revise, and audit scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, and local consistency checks. Use for manuscript sections, references, declarations, tables, figures, or submission preparation when scientific accuracy and traceability matter.

k-dense-ai avatark-dense-ai
获取
site-architecture

site-architecture

34Ksecurity

当用户想要规划、映射或重构网站的页面层级、导航、URL结构或内部链接时使用。也适用于用户提及“站点地图”、“网站地图”、“可视化站点地图”、“网站结构”、“页面层级”、“信息架构”、“IA”、“导航设计”、“URL结构”、“面包屑导航”、“内部链接策略”、“网站规划”、“我需要哪些页面”、“我应该如何组织我的网站”或“网站导航”时。只要有人在规划网站应该有哪些页面以及它们如何连接,就使用此技能。不适用于XML站点地图(那是技术SEO——请参见seo-audit)。对于SEO审计,请参见seo-audit。对于结构化数据,请参见schema。

coreyhaines31 avatarcoreyhaines31
获取
nature-downloader

nature-downloader

32Ksecurity

当用户需要合法获取学术文献全文、通过机构权限访问知网(CNKI)、检索英文开源免费文献(OA)、使用出版商 API 接口获取资源、借助浏览器机构鉴权回退获取,或下载补充材料(SI / Supporting Information)时使用。

yuan1z0825 avataryuan1z0825
获取
gws-classroom

gws-classroom

29Ksecurity

Google Classroom:管理课程、花名册和课程作业。

googleworkspace avatargoogleworkspace
获取
persona-it-admin

persona-it-admin

29Ksecurity

管理IT — 监控安全并配置Workspace。

googleworkspace avatargoogleworkspace
获取