SkillRisk: Agent Skill Scanner
Secure your AI Agent Skills
Only for Mac
Free · In‑App Purchases
Mac
Now scans OpenClaw workspaces — detect prompt injection, identity spoofing & more with 8 new security rules for AI agent skills.
Is your AI Agent safe?
As AI agents like Claude and OpenClaw become powerful daily collaborators, installing third-party Skills and MCP (Model Context Protocol) Tools carries hidden risks. A malicious skill can steal your API keys, access private files, or execute dangerous commands on your Mac.
SkillRisk is the first dedicated security scanner built for the Agentic AI era, designed to protect your digital workspace.
It analyzes your installed skills, local configurations, and custom integrations to detect potential vulnerabilities, malicious patterns, and privacy threats before they can cause harm.
KEY FEATURES:
• Comprehensive Protection for Claude & OpenClaw
Automatically locates and scans your default Claude Desktop configuration, OpenClaw environment settings, and MCP tool directories.
• Automatic Risk Detection
Instantly identify known malicious patterns, reverse shells, crypto miners, and data exfiltration scripts hidden in third-party skill code.
• Deep Folder Scanning
Drag and drop any folder, repository, or local directory containing agent skills to perform a comprehensive security audit before granting your AI agent access.
• Code Snippet Analysis
Paste individual files or raw code snippets into the instant sandbox for a quick security check before adding them to your agent workflow.
• Privacy-First Local Scanning
Your secrets stay secret. All security scanning happens locally on your Mac. Your private code, configuration files, and API keys never leave your device and are never uploaded to the cloud.
WHY CHOOSE SKILLRISK?
• Verify community-built skills and repositories before installation.
• Regularly audit your existing config.json and OpenClaw setups.
• Receive clear, visual reports categorizing threats by risk level (Safe, Warning, Critical).
• Replace time-consuming manual code reviews with instant, automated security checks.
Don't let a "helpful" skill compromise your security. Scan it with SkillRisk and build your AI workflows with confidence.
Privacy Policy: https://skillrisk.org/privacy
Terms of Use: https://skillrisk.org/terms
Ratings & Reviews
- This app hasn’t received enough ratings or reviews to display an overview.
Now supporting OpenClaw scanning!
Scan your OpenClaw workspace for security risks in SKILL.md, SOUL.md, TOOLS.md and other configuration files. Detect prompt injection, identity spoofing, memory poisoning, and more.
- New Scan OpenClaw mode with custom workspace path support
- 8 new OpenClaw-specific security rules covering prompt injection, privilege escalation, browser phishing, and more
- Updated example skills with OpenClaw-style malicious and risky samples
- Fixed Keychain access prompting for password on every launch
The developer, 帅 陈, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy .
Data Not Collected
The developer does not collect any data from this app.
Accessibility
The developer has not yet indicated which accessibility features this app supports. Learn More
Information
- Seller
- 帅 陈
- Size
- 1.6 MB
- Category
- Utilities
- Compatibility
Requires macOS 15.0 or later.
- Mac
Requires macOS 15.0 or later.
- Mac
- Languages
- English
- Age Rating
4+
- 4+
- In-App Purchases
Yes
- SkillRisk Pro Lifetime $69.99
- SkillRisk Pro Yearly $39.99
- SkillRisk Pro Monthly $5.99
- Copyright
- © 2026 ElevenApril