Helps detect permission creep in AI agent skills β flags when a skill's actual code accesses resources far beyond what its declared purpose requires, like a...
Data sourced from ClawHub. View on ClawSkills
What Permission Creep Scanner can do for your AI workflow
Detect permission creep in ai directly from your Claude conversation
Works across Claude, Cursor, OpenClaw β install once, use everywhere
One-command installation β no complex setup required
Combine with other skills to build powerful multi-step AI workflows
Try these prompts with your AI agent after installing Permission Creep Scanner
Help me get started with Permission Creep Scanner
Explains what Permission Creep Scanner does, walks through the setup, and runs a quick demo based on your current project
Use Permission Creep Scanner to detect permission creep in AI agent skills β flags when a skill's a...
Invokes Permission Creep Scanner with the right parameters and returns the result directly in the conversation
What can I do with Permission Creep Scanner in my developer & devops workflow?
Lists the top use cases for Permission Creep Scanner, with example commands for each scenario
Guides & tutorials for AI skills
The 7 AI Skills Every Software Developer Should Have Installed in 2026
After testing dozens of developer-focused AI skills, these are the seven that have proven genuinely useful across different tech stacks and workflows β not just impressive demos, but tools that hold up under daily use.
MCP Skills vs Native Claude Tools: What's the Difference and When to Use Each
Claude comes with built-in capabilities, but MCP skills extend it in ways the base model can't. Here's a clear breakdown of what each type of tool is good for, with real examples of when to reach for a skill versus relying on Claude's native abilities.
Permission Creep Scanner extends your AI assistant with the ability to helps detect permission creep in AI agent skills β flags when a skill's actual code accesses resources far beyond what its declared purpose requires, like a... Rather than leaving your conversation to handle this manually, you can ask your Claude agent directly β and it will take care of the task end-to-end, using Permission Creep Scanner as its underlying capability.
Permission Creep Scanner works across Claude, Cursor, OpenClaw through the Model Context Protocol (MCP) β an open standard that lets AI clients share tools and skills without lock-in. Because MCP is platform-agnostic by design, you install Permission Creep Scanner once and it becomes available across all your AI clients. Whether you're working in Claude for focused sessions or Cursor for integrated workflows, the skill behaves consistently.
To install Permission Creep Scanner, copy the skill folder to `~/.claude/skills/permission-creep-scanner/` for use across all your projects, or `.claude/skills/permission-creep-scanner/` for a single project. Restart Claude and the skill is immediately active β invoke it with `/permission-creep-scanner` or just describe your goal and the AI will pick it up automatically.
Permission Creep Scanner has 482 installs and is part of the growing Developer & DevOps skill ecosystem on DiscoverAISkills. The source code is open on GitHub β you can inspect it, contribute fixes, or fork it to adapt the skill for your specific setup. Like all skills on DiscoverAISkills, it is free to install and use. The broader AI skills ecosystem continues to expand as developers contribute new capabilities across categories like developer tools, data analysis, writing, automation, and more.
Place the skill folder at ~/.claude/skills/permission-creep-scanner/ for personal use (all projects), or .claude/skills/permission-creep-scanner/ for project-specific use. Restart your AI client, then invoke with /permission-creep-scanner or let the AI discover it automatically.
Permission Creep Scanner supports Claude, Cursor, OpenClaw. It integrates seamlessly with these AI platforms to extend their capabilities.
Permission Creep Scanner is free to install. Check the repository for licensing information.
Helps detect permission creep in AI agent skills β flags when a skill's actual code accesses resources far beyond what its declared purpose requires, like a...
permissionless prediction markets
Create, trade, and settle prediction markets on Base with any ERC20 collateral. Use when building prediction market infrastructure, running contests, crowdsourcing probability estimates, adding utility to tokens, or tapping into true information finance via market-based forecasting.
Permissions Broker
Interact with the Permissions Broker service to fetch data from Google APIs behind a Telegram approval gate. Use when an agent needs to read Google Drive/Doc...
Config Security Scanner
Security expert for OpenClaw deployments. Audits local configuration files for vulnerabilities in network settings, channel policies, and tool permissions. P...
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install permission-creep-scannerOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install permission-creep-scannerβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/permission-creep-scanner/π‘Extract and place the folder at the path above, then restart your agent.
Automate my developer & devops tasks using Permission Creep Scanner
Identifies repetitive steps in your workflow and sets up Permission Creep Scanner to handle them automatically
Permission Creep Scanner is categorized under Developer & DevOps. These skills help AI agents perform specialized tasks in this domain.