urlcheck
by cplusdev
Coding Agents & IDEsBrief
Companion skill for @cybrlab/urlcheck-openclaw.
Description
What This Skill Does
Verifies URLs for security threats before an agent navigates, clicks, or follows a redirect. Accepts an optional intent parameter to check whether the destination matches what the user is actually trying to do, not just whether it's malicious.
Intent-alignment checking catches cases where a URL is technically safe but not the destination the user meant to reach, which threat-only scanners miss.
When to Use It
- Checking a login link before submitting credentials
- Verifying a download URL before fetching a file
- Screening redirects in automated browsing workflows
- Confirming a payment or checkout page matches the user's intended site
- Flagging phishing links in user-provided URLs
Example Workflow
User asks: Before I open https://accounts-google.com.login-verify.net, check if it's safe to log in to my Google account
- 1
Call url_scanner_scan_with_intent with url='https://accounts-google.com.login-verify.net' and intent='log in to my Google account'
- 2
Wait up to 90 seconds for the scan to complete
- 3
Read the agent_access_directive field from the result
- 4
Check intent_alignment to see if the destination matches a Google login page
- 5
Report the directive, risk_score, and intent_alignment finding to the user
DENY directive returned with high risk_score and intent_alignment: misaligned. Agent tells the user the URL does not appear to be a legitimate Google login page and recommends not proceeding.
Requirements
- openclaw plugins install @cybrlab/urlcheck-openclaw (free tier: 100 requests/day; contact contact@cybrlab.ai for higher limits)
Installation
clawhub install cplusdev/urlcheckRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.