Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Add support email (trust-check@outtake.ai)
What This Skill Does
Checks URLs and domains for phishing, malware, brand abuse, and scams using the Outtake Trust API. Returns a verdict with confidence score and recommended action. Supports single URL checks and batch requests of up to 50 URLs.
Returns a structured verdict with confidence scores rather than just a block/allow decision, making it easier to act appropriately on uncertain results.
When to use it
- Checking a link from an email before clicking
- Verifying a domain shared in a chat message
- Scanning multiple URLs from a scraped list
- Confirming a site is safe before recommending it to users
- Reviewing suspicious links in support tickets
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Is https://suspicious-site.com safe to visit?
- 1Send POST request to /api/v1/trust/check with the URL and OUTTAKE_API_KEY
- 2Receive verdict, confidence score, safe_to_visit status, and recommended_action
- 3Evaluate verdict: malicious blocks, suspicious warns, safe clears, unknown proceeds with caution
- 4Report the verdict and recommended action to the user
verdict: malicious, confidence: 0.92, safe_to_visit: unsafe, recommended_action: block
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.