# INP-01 Direct prompt injection detection

Domain: INP Input & Prompt Security · HI-AAF v1.3 · Public review · https://humanintel.net/standard/inp/inp-01

Direct prompt injection detection is applied to user-provided inputs, using a combination of heuristic and classifier-based methods.

Direct injection, where a user attempts to override the system prompt through their input, is detected using a combination of heuristic and classifier-based methods. The agent does not disclose its system prompt or override its operating envelope in response to user-crafted inputs. Detection rates and false-positive rates are measured and reported.

## 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-01: Detection is applied to all user-facing input paths; detection rates and false-positive rates are measured; the detection pipeline is updated as new attack patterns are cataloged in SPC-08.
- 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

- Detection is applied to all user-facing input paths.
- Detection rates and false-positive rates are measured.
- The detection pipeline is updated as new attack patterns are cataloged in SPC-08.

## Framework mappings

- NIST AI RMF: MEASURE 2.7
- ISO/IEC 42001: A.8.2
- OWASP LLM Top 10: LLM01
- SOC 2 (TSC): CC7.1
- EU AI Act: Art. 15(4)
- MITRE ATLAS: Initial Access
- Singapore: MAIGF Security, AI Verify Security

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

## Related

- Cites SPC-08 Known-unsafe inputs catalog: https://humanintel.net/standard/spc/spc-08

## Cite this control

Human Intelligence. HI-AAF v1.3, INP-01 Direct prompt injection detection. Public review edition, July 2026. https://humanintel.net/standard/inp/inp-01