AGENT SKILL

auditing-access-control

This skill enables Claude to audit access control implementations in various systems. It uses the access-control-auditor plugin to identify potential vulnerabilities and misconfigurations related to access control. Use this skill when the user asks to "audit access control", "check permissions", "assess access rights", or requests a "security review" focused on access management. It's particularly useful for analyzing IAM policies, ACLs, and other access control mechanisms in cloud environments, applications, or infrastructure. The skill helps ensure compliance with security best practices and identify potential privilege escalation paths.

License 许可
MIT
最近更新
2026-11-09
Stars
★ 2
Forks
0

01 前言 Front Matter

name
auditing-access-control
description
This skill enables Claude to audit access control implementations in various systems. It uses the access-control-auditor plugin to identify potential vulnerabilities and misconfigurations related to access control. Use this skill when the user asks to "audit access control", "check permissions", "assess access rights", or requests a "security review" focused on access management. It's particularly useful for analyzing IAM policies, ACLs, and other access control mechanisms in cloud environments, applications, or infrastructure. The skill helps ensure compliance with security best practices and identify potential privilege escalation paths.

02 资源文件 3

03 SKILL.md 正文

Overview

This skill leverages the access-control-auditor plugin to perform comprehensive audits of access control configurations. It helps identify potential security risks associated with overly permissive access, misconfigured permissions, and non-compliance with security policies.

How It Works

  1. Analyze Request: Claude identifies the user's intent to audit access control.
  2. Invoke Plugin: The access-control-auditor plugin is activated.
  3. Execute Audit: The plugin analyzes the specified access control configuration (e.g., IAM policies, ACLs).
  4. Report Findings: The plugin generates a report highlighting potential vulnerabilities and misconfigurations.

When to Use This Skill

This skill activates when you need to:

  • Audit IAM policies in a cloud environment.
  • Review access control lists (ACLs) for network resources.
  • Assess user permissions in an application.
  • Identify potential privilege escalation paths.
  • Ensure compliance with access control security policies.

Examples

Example 1: Auditing AWS IAM Policies

User request: "Audit the AWS IAM policies in my account for overly permissive access."

The skill will:

  1. Invoke the access-control-auditor plugin, specifying the AWS account and IAM policies as the target.
  2. Generate a report identifying IAM policies that grant overly broad permissions or violate security best practices.

Example 2: Reviewing Network ACLs

User request: "Review the network ACLs for my VPC to identify any potential security vulnerabilities."

The skill will:

  1. Activate the access-control-auditor plugin, specifying the VPC and network ACLs as the target.
  2. Produce a report highlighting ACL rules that allow unauthorized access or expose the VPC to unnecessary risks.

Best Practices

  • Scope Definition: Clearly define the scope of the audit (e.g., specific IAM roles, network segments, applications).
  • Contextual Information: Provide contextual information about the environment being audited (e.g., security policies, compliance requirements).
  • Remediation Guidance: Use the audit findings to develop and implement remediation strategies to address identified vulnerabilities.

Integration

This skill can be integrated with other security plugins to provide a more comprehensive security assessment. For example, it can be combined with a vulnerability scanner to identify vulnerabilities that could be exploited due to access control misconfigurations. It can also be integrated with compliance tools to ensure adherence to regulatory requirements.

04 同仓库更多 Skills

sandraschi
sandraschi/documentation-mcp

Docs Research

Use MCP Central Docs server to search, ask, and retrieve documentation (FastMCP, standards, packaging).

资料检索与研究Skill与智能体开发
★ 2
sandraschi
sandraschi/documentation-mcp

wrappee-drift

Read-only, single-repo audit of a repo's tool coverage against the software it wraps (its current real API/docs, not training-data memory) and against comparable/competing wrappers. Trigger when the user says "wrappee drift" followed by a repo name, "capability audit" followed by a repo name, or asks whether a repo is missing features the wrapped software or a competitor now has. Always scoped to one named repo per invocation -- never trigger this fleet-wide or unprompted; that is explicitly against the SOP. Do NOT trigger for internal fleet-standard compliance (that is drift-scan) or strategic worth/archive decisions (that is quality-check) -- this is specifically about the gap between the repo's tool list and the wrapped software's/competitors' actual current capabilities.

★ 2
sandraschi
sandraschi/documentation-mcp

modules

暂无简介

运维与部署Skill与智能体开发
★ 2
sandraschi
sandraschi/documentation-mcp

mcp-standards

Use when developing MCP servers to access comprehensive standards for scaffolding, packaging, sampling, documentation, testing, error handling, monitoring, and CI/CD workflows.

测试与质量Skill与智能体开发
★ 2
sandraschi
sandraschi/documentation-mcp

webapp-cua-test

Run the pre-Tauri CUA click-through test (real browser, dev stack, OCR "Connected" wait, sidebar nav walk) for a fleet MCP server repo under D:\Dev\repos. Trigger when the user says "cua webapp test" or "webapp clickthrough" followed by a repo name, asks for an e2e click-through of a webapp, or asks whether a webapp boots and connects in a real browser. Not for the installed NSIS app (that is the nsis-build skill / cua-nsis-test) and not for DOM assertions (Playwright), and not for hunting fake data or dead buttons (fakefind).

测试与质量Skill与智能体开发
★ 2
sandraschi
sandraschi/documentation-mcp

ship

Final release gate for a fleet MCP server repo under D:\Dev\repos -- run all quality gates, build the release artifact, verify it, commit, push, and cut a GitHub release. Trigger this whenever the user says "ship it", "ship" followed by a repo name, "release" followed by a repo name, or asks to finalize and publish work that's already been done in a repo. This is the terminal step after assfix/nsis-build, not a substitute for them -- if the repo hasn't been assessed recently, say so before shipping rather than shipping blind.

Skill与智能体开发
★ 2