SkillAtlasSkill 详情

auditing-access-control

A model-agnostic agent-skills platform.

审核状态:已审核Quality 80Security 80

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年8月27日

Tons of Skills

A model-agnostic agent-skills platform. The canonical layer is harness-free by construction; Claude Code is currently the verified-native harness. Other harnesses remain engineering candidates until their native-path integration is verified; source research alone is never presented as public support.

Release CLI Plugins Skills GitHub Stars skills.sh Sponsor: Kobiton Buy me a monster

ko-fi

Version semantics: the release badge is this marketplace's display version. npm packages, including the ccpi CLI and publishable plugins, retain their own package versions; they are intentionally not expected to equal the display version. The version-surface checker governs the display surfaces without rewriting package semver.

Install

Inside Claude Code, one command installs the whole marketplace:

/plugin marketplace add jeremylongshore/claude-code-plugins

Or use the CLI:

pnpm add -g @intentsolutionsio/ccpi
ccpi install devops-automation-pack

Browse the marketplace · Explore plugins · Download bundles

Killer Skill of the Week — no-ai-slop by Peter Yang

Strip AI slop from any draft — named-pattern edits that keep the writer's real voice

no-ai-slop does two jobs and refuses to fake a third. In Edit mode it makes the minimum effective edit — cutting throat-clearing, weak verbs, and abstract nouns while deliberately preserving the writer's cadence, bluntness, humor, and honest admissions, so a rough draft still sounds like the same person afterward. In Detect mode it names each AI-slop pattern it finds, quotes the offending line, and gives the fix in a few words — and pointedly does NOT score the draft or guess whether an AI wrote it. That restraint is the whole point: AI detectors guess; named patterns are evidence the reader can check. MIT-licensed, single focused skill, actively maintained by Peter Yang.

"AI detectors guess. Named patterns are evidence the user can check." — Peter Yang

Grade: A | Week of July 22, 2026 (W30) | View on GitHub

Previous picks: tonone, mnemos, databricks-pack, kobiton-automate, skyvern, code-cleanup, web-analytics, token-optimizer, executive-assistant-skills, skill-creator, cursor-pack, crypto-portfolio-tracker. See all at tonsofskills.com.

Scale, labeled

Every number below names the cohort it counts and the command that reproduces it — an unlabeled count is how a corpus ends up with five contradictory answers to "how many skills."

CountCohortReproduce with
442catalog plugins (catalog-entry cohort)node scripts/generate-readme-toc.mjs over marketplace.extended.json
3,067marketplace-visible skills (distinct)node -e "import('./scripts/corpus-resolver.mjs').then(m=>console.log(m.resolveCorpus('marketplace-visible').length))"
347agent definitions in pluginsgit ls-files 'plugins/**' | grep '/agents/.*\.md'
19plugin categoriesls -d plugins/*/

📦 Live npm Downloads

Across 396 published packages in the claude-code-plugins namespace. Updated daily by GitHub Actions.

WindowAll packagesEstablished (>30d)
Last 24 hours962962
Last 7 days2,9202,916
Last 30 days12,86812,779

"Established" excludes packages first published within the last 30 days, so a bulk-publish event doesn't dominate the headline.

Top 10 by last 30 days:

#PackageLast 30d
1@intentsolutionsio/openrouter-pack556
2@intentsolutionsio/groq-pack496
3@intentsolutionsio/databricks-pack274
4@intentsolutionsio/clickhouse-pack273
5@intentsolutionsio/wallet-security-auditor263
6@intentsolutionsio/notion-pack258
7@intentsolutionsio/elevenlabs-pack244
8@intentsolutionsio/freshie-inventory-manager214
9@intentsolutionsio/supabase-pack210
10@intentsolutionsio/agency-os204

Last refreshed 2026-08-19T03:03:05.709Z.

Ways in

Five real questions, five doors — each resolves to a live, generated surface, never a hand-maintained list:

Browse by category

The 19 categories below link into the live marketplace. Plugin counts are the catalog-entry cohort — regenerated from marketplace.extended.json by this generator; the catalog itself lives on tonsofskills.com, never in this file (§ 6A of the platform blueprint).

CategoryPlugins
🤖AI & Machine Learning36
🎭AI Agents & Agency10
🔌API Development26
💼Business Tools6
👥Community21
₿Crypto & Web327
💾Database26
🎨Design2
🔧DevOps & Infrastructure36
📚Examples & Templates5
🧩MCP Servers16
📦Packages5
⚡Performance25
✅Productivity30
🎁SaaS Skill Packs106
🔐Security27
✨Skill Enhancers9
🧪Testing28
📁Analytics1

What the classes mean

Four artifact classes live in this repository, distinguished on sight and never blurred — provenance is a truth requirement here, not a UX nicety:

ClassWhat it isHow the reader can tell
Canonical skillFirst-party, harness-free, the source of truthNo .source.json in its plugin directory
Generated adapterA thin, machine-produced harness projectionLives under a generated path with a "generated — do not edit" header
First-party packageAn Intent Solutions distribution (npm, cowork zip)@intentsolutionsio scope, IS-authored license
Upstream mirrorSomebody else's work, hosted mirror-by-default.source.json present — upstream author, license, and pinned commit recorded

Certification

Not yet certified. The certification program (tiers T0–T4 with retained, hash-matched evidence) is a later epic of the platform blueprint; until its report exists, no artifact on this surface claims a tier. This line is rendered from the absence of certification-report.json — honestly, not cosmetically.

Contribute

Start with the contribution guide, then the intake and review standards every submission passes through:

Governance

Provenance

External plugins are hosted mirror-by-default: the contributor's repository stays the source of truth, every mirrored source is pinned in a content lockfile, and upstream credit — author, license, resolved commit — is recorded in the mirror itself. Improvements flow by upstreaming to the author's repository, never by silently editing the mirror. The full decision record is the external-sync model.

License

MIT for the repository scaffolding and first-party tooling; each plugin carries its own license in its manifest, and mirrored plugins keep their upstream license verbatim.

其他

中风险

  • 来源需自行核对维护者身份。
  • 包含脚本或命令调用,安装前请复核。
  • 未检测到明显外部权限要求。
  • 未检测到高风险命令。
  • 扫描发现:2 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/auditing-access-control" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/auditing-access-control" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/auditing-access-control" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/auditing-access-control" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/jeremylongshore/tons-of-skills-marketplace.git
  3. 将 "skills/.curated/auditing-access-control" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: auditing-access-control
description: Audit access control implementations for security vulnerabilities and
  misconfigurations. Use when reviewing authentication and authorization. Trigger
  with 'audit access control', 'check permissions', or 'validate authorization'.
version: 1.24.0
allowed-tools: Read, Write, Edit, Grep, Glob, Bash(security:*), Bash(scan:*), Bash(audit:*)
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- security
- authentication
- audit
compatibility: Designed for Claude Code

Access Control Auditing

Overview

Audit access control implementations across codebases, cloud configurations, and application layers for security vulnerabilities and policy violations. This skill targets IAM policies, ACLs, RBAC configurations, file permissions, and API authorization logic to identify privilege escalation paths, overly permissive grants, and violations of the principle of least privilege.

Prerequisites

  • Access to the target codebase and configuration files in ${CLAUDE_SKILL_DIR}/
  • Familiarity with the authorization model in use (RBAC, ABAC, ACL, or IAM)
  • grep, find, and standard shell utilities available via Bash
  • For cloud audits: CLI tools such as aws iam, gcloud, or az role installed and authenticated
  • Reference: ${CLAUDE_SKILL_DIR}/references/README.md for IAM best practices, ACL vulnerability patterns, and NIST/GDPR access control standards

Instructions

  1. Enumerate all access control definitions by scanning for IAM policy files, RBAC configuration, ACL definitions, middleware authorization checks, and .htaccess or equivalent files using Glob and Grep.
  2. Map each role or principal to its granted permissions, building a permission matrix that identifies which subjects access which resources at which privilege level.
  3. Evaluate each permission grant against the principle of least privilege -- flag any wildcard permissions (*), overly broad resource scopes, or administrative access granted to non-admin roles.
  4. Check for separation of duties violations where a single role combines mutually exclusive privileges (e.g., both "create user" and "approve user").
  5. Identify privilege escalation paths by tracing role inheritance chains, looking for roles that can modify their own permissions or assume higher-privileged roles.
  6. Inspect API route handlers and middleware for missing or inconsistent authorization checks -- compare route definitions against their corresponding auth guards.
  7. Verify that default-deny is enforced: confirm that unauthenticated or unauthorized requests are rejected unless explicitly allowed.
  8. Cross-reference findings against compliance requirements (NIST AC-1 through AC-25, GDPR Article 25, SOC 2 CC6.1) and flag gaps.
  9. Classify each finding by severity (critical, high, medium, low) based on exploitability and blast radius.
  10. Generate a remediation plan with specific configuration changes, code patches, or policy updates for each finding.

Output

  • Permission matrix: Role-to-resource mapping table showing all grants
  • Findings report: Each finding includes severity, affected resource, description, CWE reference (e.g., CWE-269 Improper Privilege Management, CWE-285 Improper Authorization), and remediation steps
  • Compliance gap analysis: Checklist of NIST SP 800-53 AC controls and GDPR access control requirements with pass/fail status
  • Privilege escalation paths: Diagram or list of role chains that enable escalation
  • Executive summary: Total findings by severity, top risks, and recommended priority actions

Error Handling

ErrorCauseSolution
Permission denied reading config filesInsufficient filesystem accessRun with elevated permissions or request read access to the target directory
IAM CLI command not foundCloud CLI tools not installedInstall aws-cli, gcloud, or az and authenticate before running cloud audits
Empty role/permission scan resultsIncorrect glob patterns for the frameworkAdjust search patterns to match the target framework (e.g., @Roles() for NestJS, [Authorize] for .NET)
Timeout scanning large codebasesToo many files in scopeNarrow the scan scope with --exclude patterns for node_modules, vendor, or dist directories
Inconsistent policy formatMixed IAM policy versions or formatsNormalize policies to a single format before analysis; flag format inconsistencies in the report

Examples

Auditing a Node.js Express API

Scan route definitions in ${CLAUDE_SKILL_DIR}/src/routes/ for missing authorization middleware. Grep for router.post, router.put, router.delete and verify each has a corresponding authMiddleware or requireRole() call. Flag any state-changing endpoint lacking authorization as CWE-862 (Missing Authorization), severity high.

Reviewing AWS IAM Policies

Parse all JSON policy files in ${CLAUDE_SKILL_DIR}/infra/iam/. Flag policies containing "Effect": "Allow" with "Resource": "*" or "Action": "*" as CWE-269 (Improper Privilege Management), severity critical. Recommend scoping to specific ARNs and actions per the principle of least privilege.

RBAC Configuration Audit

Analyze role definitions in ${CLAUDE_SKILL_DIR}/config/roles.yaml. Build a permission matrix, identify roles with overlapping admin-level privileges, and flag any role that can both create and approve its own resources as a separation-of-duties violation (NIST AC-5), severity medium.

Resources

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!