Send inputs that maximize tokens, trigger repeated retries, create long tool loops, or fan out into many model calls.
LLM10:2025
Unbounded Consumption
How attackers or faulty workflows can drive excessive model calls, token use, context growth, tool loops, compute cost, or service disruption.
Step 01
Input
Step 02
Model
Step 03
Tool / Data
Step 04
Impact
What it is
The application does not enforce practical budgets, rate limits, loop controls, queue limits, tenant quotas, or graceful degradation for AI workloads.
Why it matters
Excessive requests or agent loops can exhaust capacity and increase cost while legitimate work waits. Per-request limits alone may miss a large number of individually valid requests.
Failure path
One way this failure can develop.
Use this example to locate the input, permission or application check that would interrupt the sequence in your system.
Exploit missing tenant quotas, caching, circuit breakers, or workflow ceilings.
Drive cost, latency, or availability impact before operators can respond.
Defenses
Controls worth checking.
Check where each control runs, who owns it and how you will test it again after a prompt, model or workflow change.
Set budgets and ceilings
Limit tokens, context size, tool iterations, retries, runtime, queue depth, and tenant-level spend for each workflow.
Rate-limit expensive paths
Apply rate limits, abuse detection, caching, and backpressure to AI endpoints, RAG queries, and agent loops.
Fail safely
Use circuit breakers, partial-response behavior, and clear user messaging when an AI workflow hits limits.
Signals and control gaps
- Unexpected spikes in token usage, retries, tool loops, queue depth, or model cost.
- Long-running requests with no workflow ceiling.
- One user, tenant, or job consuming disproportionate AI capacity.
Questions for your team
- What is the maximum cost of one request, one user, and one tenant?
- Can an agent loop indefinitely through tools or retries?
- What happens when model, vector, or tool providers slow down?