Slide 7 of 28
Part 1 — The ProblemSlide 7
Slide 7 · Boundaries
AG07 is specifically about the communication channel between agents. Three things it is not about.
Not about manipulating an agent through its input from a user or external source

If an attacker sends a malicious prompt directly to an agent — through a chat interface, an API, or any channel the agent exposes to the outside world — that is direct input manipulation. AG07 is about the messages agents send to each other inside the pipeline. The attack surface is the channel between agents, not the channel between a user and an agent.

Not about an agent having too many permissions or taking unauthorized actions on its own

If an agent exceeds its intended scope because of how it was configured — because it was given write access to production when it should only have staging access, for example — that is an authorization or permission scoping issue. AG07 is about the communication that coordinates agents, not about what individual agents are permitted to do when they operate correctly.

Not about an agent failing due to incorrect logic or a bug in its code

If an agent misinterprets a legitimate message because of a logic error or software bug, that is a reliability or quality issue. AG07 requires that the communication channel itself was exploited — that a message was forged, tampered with, intercepted, or replayed by an attacker or compromised component.

AG07 is:

An attacker (or compromised component) exploited a weakness in the channel, protocol, or message format that agents use to communicate with each other — forging agent identity, tampering with message content, intercepting sensitive data in transit, or replaying previously valid messages — causing one or more agents to perform actions that the legitimate orchestrator never authorized.

← Back Why this is new →