Skip to content
StrikeCyberStrikeCyber
Field Manual · Attack technique

Excessive Agency

Reviewed 13 November 2026Attack technique 1 min read

Quick answer

Excessive agency is when an AI system has more permissions, tools or autonomy than its task requires. It is the reason a successful prompt injection becomes a real incident: the more an AI agent can do, the more an attacker who controls it can do. It is listed in the OWASP Top 10 for LLM Applications.

On this page
01

How It Happens

Teams building agents tend to grant broad access so the agent can handle any request: full mailbox access instead of read-only, a database account that can write as well as read, an API token with administrator scope. Each extra permission is unused most of the time, until an attacker hijacks the agent through prompt injection or a poisoned tool.

02

Three Forms of Excess

  • Excessive functionality: tools the agent does not need, such as delete or send functions.
  • Excessive permissions: credentials with broader scope than the task.
  • Excessive autonomy: sensitive actions taken without human confirmation.
03

How to Test for It

  1. List every tool, credential and permission each agent holds.
  2. Compare that list with what the agent's tasks actually require.
  3. Attempt to hijack the agent and use each unnecessary capability.
  4. Check which actions run without human approval.
  5. Report the blast radius: the worst realistic outcome of a compromised agent.
04

How to Reduce the Risk

Apply least privilege to agents exactly as you would to staff accounts, remove unused tools, scope credentials to the task, require confirmation for actions that send, delete, pay or change access, and log every tool call.

05

Regulatory and Framework Context

For Australian organisations, least privilege for AI agents extends the Essential Eight principle of restricting administrative privileges to a new class of identity.

Latest intel on this topic

Updated hourly from the daily briefing.

Common questions

Is an AI agent an identity?

In practice, yes. It holds credentials and acts on systems, so it should be governed like a service account: scoped, reviewed and monitored.

What is a human-in-the-loop control?

A requirement that a person confirms an AI-proposed action before it runs, used for sensitive actions such as payments, deletions and external messages.

Change log

  1. 13 November 2026First published.
1300 654 898