Agent goal hijack
Over several steps, the attacker replaces what the agent is trying to achieve. Each step can look reasonable; the course as a whole serves the attacker.
- ASI01:2026 Agent Goal Hijack
- LLM01:2026 Prompt Injection
- LLM03:2026 Excessive Agency
- AML.T0051.001 LLM Prompt Injection: Indirect
How it works
- 1Agents plan: they break a request into steps and revise the plan as they read results.
- 2Content read mid-task can add or change goals, so the agent keeps working, just towards something else.
- 3Because each action is plausible on its own, per-call checks miss it; the change shows only in the sequence.
What to watch for
- The plan drifts from the user's request
- New sub-goals appear after the agent reads outside content
- Steps that individually pass but together reach data or systems outside the task
How to defend
- Keep the user's goal explicit and check actions against it.
- Bound what a single task may reach.
- Review long-running agents' trajectories, not only single calls.