A challenge-response identity verification skill that adds a human-in-the-loop security layer before your AI agent performs sensitive operations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install stranger-danger
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install stranger-danger using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Stranger-Danger?
Stranger-Danger provides a robust security gate for AI agents by implementing a safe word or challenge-response system. It ensures that sensitive operations—such as revealing API keys, deleting databases, or accessing passwords—are only executed after the user provides the correct answer to a predefined secret question. This adds a critical layer of protection against accidental data loss or unauthorized access during automated workflows within Openclaw Skills.
Built with security-first principles, the skill integrates directly with the macOS Keychain to store verification data safely. This prevents sensitive credentials from being stored in plain text and ensures that Openclaw Skills can operate with a high degree of trust even when handling privileged information.
Stranger-Danger Use Cases
- Requesting access to stored API keys, tokens, or plaintext secrets
- Executing commands to delete or irreversibly modify production databases
- Authorizing the exfiltration of sensitive files or personal information via Openclaw Skills
- Verifying user identity during unusual or high-risk AI agent behavioral patterns
How Stranger-Danger Works
- The user initializes the skill using the setup command to define a secret question and answer.
- The system hashes the answer using bcrypt and stores it securely in the macOS Keychain.
- During a session, when an AI agent identifies a high-risk request, it triggers the verification process.
- The agent presents the user with the stored secret question and awaits input.
- The skill compares the input against the secure hash using the stranger-danger verify command.
- Upon success (exit code 0), the AI agent is authorized to proceed with the requested sensitive operation.
Stranger-Danger Setup
To begin securing your Openclaw Skills with identity verification, follow these installation steps:
# Install the skill via your preferred package manager
npm install stranger-danger
# Configure your secret question and answer
stranger-danger setup
# Run a test to ensure the macOS Keychain integration is working correctly
stranger-danger test
Stranger-Danger Data Schema & Taxonomy
| Component | Storage Location | Security Method |
|---|---|---|
| Secret Answer Hash | macOS Keychain | Salted bcrypt hash |
| Secret Question | ~/.openclaw/stranger-danger.json | JSON configuration |
| CLI Dependencies | System Binaries | node, security (macOS) |
Stranger-Danger Advanced Features
- Enterprise-grade security utilizing the macOS Keychain for persistent, encrypted storage
- Localized bcrypt hashing to ensure that raw answers are never saved to the filesystem
- Automatic integration hooks for Openclaw Skills to pause execution until human verification is met
- Rapid reset and testing commands to maintain and audit security protocols periodically
SKILL.md
Loading
Related Openclaw Skills
spaces-listener
A robust tool for capturing, transcribing, and summarizing live or archived X/Twitter Spaces using advanced AI models.
Konteks
A persistent context layer that connects your AI agent to Konteks for shared memory, task management, and project organization.
Grab
A multi-platform content downloader and archiver that preserves videos, transcripts, and AI-generated summaries from social media.
fastclaw-relay
Bridges your local OpenClaw Gateway to the FastClaw iOS app via Convex real-time cloud synchronization.
AHC-Automator: Alan Harper Composites Workflow Automation
A specialized automation suite that synchronizes email communication, ClickUp project management, and Pipedrive CRM for composite manufacturing workflows.
GitHub Knowledge Base Manager
An integrated system for searching, cloning, and cataloging GitHub repositories within a local knowledge base.
METADATA
Featured*
