Hackers Could Abuse Microsoft Entra AI Agents to Hijack Enterprise Accounts Without Stealing Passwords
Hackers can hijack enterprise accounts by tricking users into approving fake AI agents.
Researchers have discovered a new technique called BluePhishing that allows attackers to compromise Microsoft 365 environments by tricking users into approving malicious AI agents. This method bypasses traditional password theft and login screen spoofing by exploiting Microsoft Entra Agent ID and OAuth consent phishing principles. Proofpoint researchers identified the technique but have not yet observed it in real-world attacks.
AI summary of the linked source. Not reviewed by an editor. How this works
Run Proofpoint?
Get an email when a new story names Proofpoint, usually within the hour.
Free. Your list stays private and never appears in a subject line. One click stops it. How Vendor Watch worksPrivacy
The lesson from this incident
Full lessonAttackers discovered a technique to compromise Microsoft 365 environments by deceiving users into granting OAuth consent to malicious AI agents registered in Microsoft Entra, entirely bypassing the need to steal passwords or spoof login pages. Because users are conditioned to approve OAuth permission prompts without scrutinizing what access they are actually delegating, this social-engineering vector is highly effective. The abuse of legitimate platform features—Agent IDs and OAuth flows—makes the attack difficult to detect with traditional credential-monitoring tools. This highlights that as AI-integrated platforms expand delegated permission models, users and administrators must treat agent/app consent requests with the same suspicion as phishing emails.
What helps against this
How we list vendors
- Phishing-resistant MFA
A stolen password, or a user who taps Approve on a push prompt, is no longer enough to log in.
- Identity governance and single sign-on
People who leave or change roles lose access everywhere at once, and forgotten accounts stop piling up.
- AI application security
Prompt injection, data leaks through AI tools and unapproved AI use get caught.