Updated 2w ago
by bruc3van
agent-skills-guard
一款提供Agent Skills安全扫描和可视化管理的桌面应用 | A desktop application that provides security scanning and visual management for Agent Skills.
390 GitHub stars (390)
+1 in 20 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | 0 |
| Sep 30 | 0 |
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | +1 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
- 29 skills (29 skills found in its SKILL.md files)
- 35 forks (35 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add bruc3van/agent-skills-guard
Asks which skills and agents to install. Just one: npx skills add bruc3van/agent-skills-guard --skill allowed-tools-mismatch-counterexample — add -g for every project.
Claude Code
git clone https://github.com/bruc3van/agent-skills-guardcp -r "agent-skills-guard/test/test-skills/negative-generated/allowed-tools-mismatch" ~/.claude/skills/
Copies the allowed-tools-mismatch-counterexample skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add bruc3van/agent-skills-guard
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 29 of 82 files.
-
allowed-tools-mismatch-counterexample
Generated counterexample declaring narrow tool access while scripts perform network activity
test/test-skills/negative-generated/allowed-tools-mismatch/SKILL.md on GitHub (opens in a new tab) -
file-magic-mismatch-counterexample
Generated counterexample containing a static asset whose extension does not match its content
test/test-skills/negative-generated/file-magic-mismatch/SKILL.md on GitHub (opens in a new tab) -
hard-trigger-shell
Generated counterexample containing destructive shell hard triggers for scanner verification
test/test-skills/negative-generated/hard-trigger-shell/SKILL.md on GitHub (opens in a new tab) -
homoglyph-obfuscation-counterexample
Generated counterexample containing mixed-script lookalike account names
test/test-skills/negative-generated/homoglyph-obfuscation/SKILL.md on GitHub (opens in a new tab) -
pipeline-exfil-counterexample
Generated counterexample containing a multi-stage sensitive data exfiltration pipeline
test/test-skills/negative-generated/pipeline-exfil/SKILL.md on GitHub (opens in a new tab) -
prompt-injection-counterexample
Generated counterexample containing direct instruction override attempts
test/test-skills/negative-generated/prompt-injection/SKILL.md on GitHub (opens in a new tab) -
yao-codereview-hskill
提供专业的代码审查服务,检查代码质量、安全漏洞、性能问题和最佳实践。支持多种编程语言和框架。
test/test-skills/negative-generated/yao-codereview-hskill/SKILL.md on GitHub (opens in a new tab) -
yao-knowledge-hskill
构建和维护领域知识图谱,帮助团队整理概念关系、术语定义和知识体系。支持技术、产品、业务等多种知识域。
test/test-skills/negative-generated/yao-knowledge-hskill/SKILL.md on GitHub (opens in a new tab) -
yao-techselect-hskill
帮助开发团队进行技术选型决策,提供框架对比、架构评估和最佳实践建议。适用于需要在多个技术方案中做出选择的场景。
test/test-skills/negative-generated/yao-techselect-hskill/SKILL.md on GitHub (opens in a new tab) -
bruce-drawio
**Use this skill** when the user wants to create any diagram: flowchart, architecture, UML (sequence/class), ER, mindmap, network topology, or any visual diagram. Trigger words: "draw", "diagram", "flowchart", "architecture", "UML", "sequence diagram", "mindmap", "ER diagram", "network topology", "visualize", "draw.io", "drawio". Workflow: understand requirements -> generate drawio XML directly -…
test/test-skills/positive-real/agents-bruce-drawio/SKILL.md on GitHub (opens in a new tab) -
bruce-doc-converter
双向文档转换工具,将 Word (.docx)、Excel (.xlsx)、PowerPoint (.pptx) 和 PDF (.pdf) 转换为 AI 友好的 Markdown,或将 Markdown (.md) 转换为 Word (.docx)(支持 Mermaid 图表自动渲染为 PNG)。当用户请求文档转换、导出、读取、分析 Office/PDF/Markdown 文件,或上传这些格式并询问内容时使用。
test/test-skills/positive-real/agents-doc-converter/SKILL.md on GitHub (opens in a new tab) -
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing image…
test/test-skills/positive-real/agents-docx/SKILL.md on GitHub (opens in a new tab) -
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
test/test-skills/positive-real/agents-frontend-design/SKILL.md on GitHub (opens in a new tab) -
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working…
test/test-skills/positive-real/agents-pptx/SKILL.md on GitHub (opens in a new tab) -
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
test/test-skills/positive-real/agents-skill-creator/SKILL.md on GitHub (opens in a new tab) -
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especia…
test/test-skills/positive-real/agents-xlsx/SKILL.md on GitHub (opens in a new tab) -
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the…
test/test-skills/positive-real/codex-system-imagegen/SKILL.md on GitHub (opens in a new tab) -
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs questions, use the Codex manual helper first for broad Codex self-knowledge, and restri…
test/test-skills/positive-real/codex-system-openai-docs/SKILL.md on GitHub (opens in a new tab) -
plugin-creator
Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries for plugin ordering and availability metadata, or update an existing local plugi…
test/test-skills/positive-real/codex-system-plugin-creator/SKILL.md on GitHub (opens in a new tab) -
skill-installer
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
test/test-skills/positive-real/codex-system-skill-installer/SKILL.md on GitHub (opens in a new tab) -
doc-curl-antipattern
Rule matrix negative fixture - documentation mentions curl-pipe-shell as an antipattern to avoid; not intended for production deployment.
src-tauri/tests/fixtures/security/rule_matrix/p0-negative/doc-curl-antipattern/SKILL.md on GitHub (opens in a new tab) -
env-var-safe-shell
Rule matrix negative fixture - safe environment variable usage without piping; not intended for production deployment.
src-tauri/tests/fixtures/security/rule_matrix/p0-negative/env-var-safe-shell/SKILL.md on GitHub (opens in a new tab) -
js-fetch-mock
Rule matrix negative fixture - mock fetch calls in test setup; not intended for production deployment.
src-tauri/tests/fixtures/security/rule_matrix/p0-negative/js-fetch-mock/SKILL.md on GitHub (opens in a new tab) -
js-fs-example
Rule matrix negative fixture - example file system usage in documentation; not intended for production deployment.
src-tauri/tests/fixtures/security/rule_matrix/p0-negative/js-fs-example/SKILL.md on GitHub (opens in a new tab) -
path-safe-realpath
Rule matrix negative fixture - uses realpath to validate file paths; not intended for production deployment.
src-tauri/tests/fixtures/security/rule_matrix/p0-negative/path-safe-realpath/SKILL.md on GitHub (opens in a new tab) -
pdf-safe
Rule matrix negative fixture - plain text file with .pdf extension marker; not intended for production deployment.
src-tauri/tests/fixtures/security/rule_matrix/p0-negative/pdf-safe/SKILL.md on GitHub (opens in a new tab) -
socket-localhost
Rule matrix negative fixture - socket connection to localhost only; not intended for production deployment.
src-tauri/tests/fixtures/security/rule_matrix/p0-negative/socket-localhost/SKILL.md on GitHub (opens in a new tab) -
sql-parameterized
Rule matrix negative fixture - uses parameterized SQL queries safely; not intended for production deployment.
src-tauri/tests/fixtures/security/rule_matrix/p0-negative/sql-parameterized/SKILL.md on GitHub (opens in a new tab) -
subprocess-test-example
Rule matrix negative fixture - subprocess usage in test helper; not intended for production deployment.
src-tauri/tests/fixtures/security/rule_matrix/p0-negative/subprocess-test-example/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.