Medium Severity

Service abuse: Upwork callback scam

Labels

Callback Phishing
Social engineering
Out of band pivot
Natural Language Understanding
Sender analysis

Description

Detects inbound messages sent from Upwork's root domain where NLU classification of the thread body identifies callback scam intent with medium or high confidence, indicating the platform is being abused to lure recipients into calling a fraudulent number.

References

No references.

Sublime Security
Created Oct 22nd, 2026 • Last updated Oct 22nd, 2026
Feed Source
Sublime Core Feed
Source
GitHub
type.inbound
and sender.email.domain.root_domain == "upwork.com"
and any(ml.nlu_classifier(body.current_thread.text).intents,
        .name == "callback_scam" and .confidence != "low"
)
MQL Rule Console
•Docs•Learning Labs

Playground

Test against your own EMLs or sample data.

Share

Post about this on your socials.

Get Started. Today.

Managed or self-managed. No MX changes.

Get Started
Deploy and integrate a free Sublime instance in minutes.
Get Started