liveBook · Manning

Trust relationship

As explained in AI Governance

A trust relationship is an expectation that another entity’s requests or actions are legitimate.

A trust relationship is an expectation that another entity’s requests or actions are legitimate. In a multi-agent system, that expectation can let hidden instructions travel from one agent to another and trigger access the first agent should not have. section 4.2.1

ClaimAssist and scheduling

An attacker embeds hidden instructions in a claim. ClaimAssist asks the scheduling agent to check availability; trusting the request, that agent follows the instructions and retrieves the adjuster’s full calendar, including other claimants’ visit addresses. section 4.2.1

Table 4.1 How each additional ClaimAssist feature increases the security risk
Version
Environment
Input
Model
Data
Ability to Act
Autonomy
V1: FAQ Bot
Yes
Yes
No
No
No
No
V2: FAQ Bot running on an unvetted model
Yes
Yes
Yes
No
No
No
V3: Personalized Assistant
Yes
Yes
Yes
Yes
No
No
V4: Fine-tuned Assistant
Yes
Yes
Yes
Yes
No
No
V5: Action-Enabled Assistant
Yes
Yes
Yes
Yes
Yes
No
V6: Agentic Assistant
Yes
Yes
Yes
Yes
Yes
Yes

Compare how ClaimAssist’s security exposure grows as it moves from a FAQ bot to an agentic assistant with the ability to act. section 4.2.1

How AI Governance covers it

How deep it goes
Illustrates a trust failure through a scenario and links expanding capabilities to broader controls and logging.
Examples
Uses ClaimAssist and a scheduling agent to show hidden instructions leading to exposure of claimants’ visit addresses.
What you can do after
Evaluate whether controls and logging match an agent’s exposure and ability to act.
How it connects
Connects trust relationships with AI agents, input validation, tool calls, and logging.

Also explained in

Compare how 2 books explain trust relationship →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of AI Governance. The section links point to the parts of the book it draws on.