BluePhishing research shows OAuth consent phishing can create hidden AI agent identities in Microsoft Entra
RESEARCHProofpointredteam/daily · 1 source
- Severity
- Medium
- Sources
- 1
What happened
Researchers at Proofpoint demonstrated a proof-of-concept attack called BluePhishing. A victim only needs to click once to approve a request, which creates lasting hidden accounts for AI agents inside their Microsoft organisation. Proofpoint has not seen this technique used in real attacks.
Like I’m new · Written by AI from 1 source · Wrong?
What to do
- Be cautious about approving OAuth consent requests from applications you do not recognise.
- Review whether any unexpected agent identities have appeared in your Microsoft Entra tenant.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
GBHackers
Who and what is in it
Companies