AWS has proposed a useful way to simplify the security debate around agents: treat several familiar risks as failures of delegation. Prompt injection concerns what the system is allowed to trust, excessive agency concerns what it may do and information disclosure concerns what it may access.

The framework separates delegation into three control points. Input delegation determines which instructions are trusted. Tool delegation defines the actions an agent may perform. Retrieval delegation limits the information it may fetch. AWS illustrates the danger with a crafted instruction hidden in retrieved content that causes an agent to query or expose information it should not touch.

The value of the model is organisational as much as technical. Security teams can test each delegation boundary instead of treating 'agent safety' as one vague control problem. A basic exercise is to plant an unauthorised instruction in a document the agent can retrieve, then observe whether policy, identity or approval controls stop the action.

AWS positions Amazon Bedrock AgentCore as a way to enforce these boundaries, so its product claims need independent validation. The underlying principle is platform-neutral: every transfer of authority should be explicit, narrow, observable and reversible.

Execution Level Governance- What audit-ready agent governance actually looks like
David Girvin, founder and CEO of Assury argues that model-in-the-loop review, AI governing AI, is fundamentally unreliable for regulated environments: even the best-performing models miss a meaningful share of violations, the reviewing model is typically provided by the same vendor being reviewed, and prompt injection or context poisoning can compromise both the acting agent and its supposed overseer simultaneously. He makes the case for deterministic, architecturally enforced controls instead, walking through Assury’s approach of autonomy zones, session risk accumulation, and credential starvation, which lets a compromised agent be cut off from its tools instantly rather than relying on time-boxed access. The conversation touches on why David is sceptical of just-in-time credentialing as a solution for agent security more broadly, since agent sessions don’t run on predictable human timescales, along with the current gap between how identity and security vendors are pitching agent protection and what he sees happening at the execution layer in practice. He also discusses the compliance and audit implications of probabilistic decision-making, arguing that regulated industries will increasingly need tamper-evident, hash-chained audit trails that can withstand scrutiny from auditors and regulators who are only beginning to understand agentic risk, and reflects on a named frontier lab’s own published framework as an example of the gap between research and practitioner reality. Elsewhere, David reflects candidly on building a bootstrapped security company in an increasingly crowded market, why he turned down aggressive VC funding to stay in control of the product, and what a credible third-party assessment of his own gateway would need to look like given that Assury sits directly in the execution path for every customer’s agents.
BrightTALK
Share this post
The link has been copied!