bruc3van/agent-skills-guard - Page 2

trigger-short-desc

Too short.

Source text: Undetermined

undeclared-network

Rule matrix security fixture for undeclared_network used by security rule matrix integration tests; not intended for production deployment.

vague-helper

A helpful tool utility assistant service agent for tasks

hidden-data

Rule matrix security fixture for hidden-data used by security rule matrix integration tests; not intended for production deployment.

hidden-script

Rule matrix security fixture for hidden_script used by security rule matrix integration tests; not intended for production deployment.

missing-license

Rule matrix security fixture for missing_license used by security rule matrix integration tests; not intended for production deployment.

pycache

Rule matrix security fixture for pycache used by security rule matrix integration tests; not intended for production deployment.

assets-ignore

Rule matrix security fixture for assets_ignore used by security rule matrix integration tests; not intended for production deployment.

assets-suspicious-url

Rule matrix security fixture for assets_suspicious_url used by security rule matrix integration tests; not intended for production deployment.

prompt-ignore

Rule matrix security fixture for prompt_ignore used by security rule matrix integration tests; not intended for production deployment.

prompt-unrestricted

Rule matrix security fixture for prompt-unrestricted used by security rule matrix integration tests; not intended for production deployment.

fake-md-pe

Rule matrix security fixture for fake_md_pe used by security rule matrix integration tests; not intended for production deployment.

base64-exec

Rule matrix security fixture for base64_exec used by security rule matrix integration tests; not intended for production deployment.

compound-laundering

Rule matrix security fixture for compound_laundering used by security rule matrix integration tests; not intended for production deployment.

download-chmod

Rule matrix security fixture for download-chmod used by security rule matrix integration tests; not intended for production deployment.

env-harvest

Rule matrix security fixture for env_harvest used by security rule matrix integration tests; not intended for production deployment.

fetch-execute

Rule matrix security fixture for fetch_execute used by security rule matrix integration tests; not intended for production deployment.

pipeline-find-exec

Rule matrix security fixture for pipeline-find-exec used by security rule matrix integration tests; not intended for production deployment.

sensitive-exfil

Rule matrix security fixture for sensitive_exfil used by security rule matrix integration tests; not intended for production deployment.

homoglyph

Rule matrix security fixture for homoglyph used by security rule matrix integration tests; not intended for production deployment.

invisible-ctrl

Rule matrix security fixture for invisible-ctrl used by security rule matrix integration tests; not intended for production deployment.

zero-width

Rule matrix security fixture for zero-width used by security rule matrix integration tests; not intended for production deployment.

allowed-tools-mismatch-counterexample

Generated counterexample declaring narrow tool access while scripts perform network activity

file-magic-mismatch-counterexample

Generated counterexample containing a static asset whose extension does not match its content

hard-trigger-shell

Generated counterexample containing destructive shell hard triggers for scanner verification

homoglyph-obfuscation-counterexample

Generated counterexample containing mixed-script lookalike account names

pipeline-exfil-counterexample

Generated counterexample containing a multi-stage sensitive data exfiltration pipeline

prompt-injection-counterexample

Generated counterexample containing direct instruction override attempts

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",…

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。

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…

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…

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,…

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…

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…

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…

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.