As organizations rapidly adopt AI, Microsoft Entra’s agent identity model introduces new capabilities, while exposing a largely uncharted attack surface.
BluePhishing is an evolution of classic OAuth consent abuse, in which attackers socially engineer victims into granting consent to a malicious agent blueprint for initial access.
By exploiting gaps in visibility and governance around emerging AI agent adoption, attackers can abuse one-time consent links to create agent identities in target tenants, obtain access tokens, and operate with the privileges assigned to those agents.
Microsoft Entra Agent ID is an identity and security framework that extends Entra to AI agents and shares several similarities with the existing application model. An agent blueprint (analogous to an app registration) defines the template for an agent, including its configuration and credentials.
An agent identity is a specific instance created from a blueprint. There can be up to 250 agent identities associated with a blueprint.
Microsoft 365 Message Center announcement MC1506733 details that default Microsoft Entra users will be able to create agent blueprints by default from November 2026, increasing organizational exposure to agent identity abuse and malicious consent scenarios.
The attack rests on a single user action. Dr. Mohamed Al Kuwaiti, Chairman of the UAE Cybersecurity Council, has said that more than 85% of cyber threats begin with an incorrect or unintended click by an average user. In BluePhishing, that click is a consent approval, and it is enough to give an attacker a foothold inside the organization.
When a victim grants consent to the agent blueprint (for example, via a consent link), a blueprint principal (analogous to a service principal) is created in the victim’s tenant.
The blueprint principal is automatically assigned a permission that cannot be revoked and allows the attacker to create agent identities in the victim tenant. The created agent identities can inherit the permissions assigned from the blueprint.
The attacker can then use the client credential configured on the blueprint to acquire tokens for those agent identities, enabling persistent access and further exploitation.
Required resource access (RRA) defines a static set of permissions upfront, while inheritable permissions ensure that permissions can be inherited by agent identities created from that blueprint.
While designed to simplify agent deployment, RRA and inheritable permissions can be used by an adversary to bundle broad permissions into a single one-time consent link, and ensure the consented permissions are automatically inherited across all agent identities.
According to Microsoft documentation, inherited permissions are not visible in the Entra portal or via Microsoft Graph, and only observable in the token contents at runtime. This lack of visibility could limit a defender’s ability to audit agent identities such as those operating with risky permissions.
Organizations should raise user awareness of the risks associated with agent consent, particularly when granting permissions to ‘third-party’ agents from untrusted sources. Much like user consent settings limit users from granting consent to third party apps, these settings also extend to agent blueprints and their agent identities.
The agent blueprint ID is consistent across all tenants that consent to it, providing a common indicator to detect or remove known malicious agents.
Applying the principle of least privilege will limit the impact of an agent compromise, utilizing controls such as Conditional Access policies for agents and Entra ID protection for agents. For monitoring, agent and blueprint events are surfaced in the audit log, in a similar way to app consent operations.
BluePhishing can be considered the next iteration of app consent phishing, inheriting many of its advantages. Like app consent phishing, it leverages legitimate, user-consented identities, allowing attackers to operate within trusted contexts. However, the agent identity framework provides distinct advantages.
Awareness of this emerging attack vector remains low, and users may be more willing to authorize AI agents without fully considering the security implications. While requests for broad application permissions can raise suspicion, autonomous behavior is a defining characteristic of agents and is therefore more readily accepted, particularly with environments already containing large numbers of agent identities.
Finally, the potential impact of compromise can be greater: a single blueprint can create up to 250 agent identities enabling compromise at scale. This dedicated agent identity framework also establishes a new paradigm for AI-driven post-exploitation, extending attacker capabilities beyond those enabled by traditional app consent phishing.











