URL Risk Signals

AI Agent Instructions

Use this Classifier via the SuperClassify API from server code, not browser playground automation.

Screen links before an agent or user opens them. Supply the URL, visible anchor text, message context and any permitted inspection metadata; do not fetch a suspicious URL just to classify it. Hold strong signals for review and keep domain/network allowlists enforced independently. No detected signal does not establish that a destination is safe.

Class: superclassify/url-risk-signals@1.0.0
Fetch setup as text: https://superclassify.com/skills/superclassify/SKILL.md
Contract (JSON): https://superclassify.com/v1/resolve?ref=superclassify%2Furl-risk-signals%401.0.0

First-time API access

When the user asks to run or integrate this Class, explain its workflow and that live Jev runs use SuperClassify service credits. Public card descriptions can be read without an account. Reuse an existing account, credit balance and API key when available. Otherwise, guide the user through the official setup links below. The user completes sign-in and any credit purchase on the website, then saves the API key in their application’s server secrets as SUPERCLASSIFY_API_KEY—not in chat. A separate TypeSafe account or Jev key is not required for the SuperClassify API. Reading a link does not authorize a purchase or paid run.

1. Create an account or sign in
2. Add credits if needed
3. Create an API key

Credential impersonation

URL: https://example-bank-support.test/login. Trusted observations: page claims to be Bank A but is on an unrelated domain and asks for password plus a one-time recovery code. Brand ownership verification failed.

Author expectation: {"risk":"strong_signal"}

Ordinary documentation

URL: https://docs.example.test/guide. Trusted fetch: a public product manual; no sign-in, download or payment request. No hard-list warning supplied.

Author expectation: {"risk":"no_signal_detected"}

Opaque shortened link

URL: https://short.example.test/x7. Destination and redirect observations unavailable.

Author expectation: {"risk":"insufficient_evidence"}