# INP-06 Input size and complexity limits

Domain: INP Input & Prompt Security · HI-AAF v1.3 · Public review · https://humanintel.net/standard/inp/inp-06

Input size and complexity limits are enforced to prevent context-window flooding and denial-of-service.

Limits on input size and complexity, token counts, nesting depth, attachment counts, are enforced to prevent context-window flooding, resource exhaustion, and denial-of-service attacks. The limits are tuned to the agent's operating envelope and are enforced before the input reaches the model.

## Maturity

- L1 Ad hoc: Controls exist informally; documentation is incomplete; no consistent review.
- L2 Documented: Controls are written down; ownership is assigned; review cadence is defined.
- L3 Operated: Controls are followed in practice; evidence is collected; deviations are tracked. Published criterion for INP-06: Limits are documented and enforced for all input paths; limit values are tuned to the agent's operating envelope; limit-exceeded events are logged and reviewed.
- L4 Measured: Control effectiveness is measured against documented thresholds; trends are reported.
- L5 Continuously Improved: Controls evolve based on incident learning; maturity gains are evidenced over time.

## Evidence an assessor asks for

- Limits are documented and enforced for all input paths.
- Limit values are tuned to the agent's operating envelope.
- Limit-exceeded events are logged and reviewed.

## Framework mappings

- OWASP LLM Top 10: LLM05
- SOC 2 (TSC): A1.1
- EU AI Act: Art. 15(4)
- Singapore: MAIGF Security, AI Verify Robustness

Mappings are directional: meeting this control evidences but does not by itself satisfy the external requirement.

## Cite this control

Human Intelligence. HI-AAF v1.3, INP-06 Input size and complexity limits. Public review edition, July 2026. https://humanintel.net/standard/inp/inp-06