Skip to content
Human Intelligence seal
Human Intelligence
§ I · Domain INP · Control 2 of 10
Control
INP-02
Edition
v.1.3
Status
Public review

INP · Input & Prompt Security · Critical

INP-02Indirect prompt injection defense

Indirect prompt injection defense is applied to content returned from tools, retrieval systems, web pages, emails, documents, and agent memory. Such content is treated as untrusted data and is not executed as instruction without explicit user confirmation.

Indirect injection, where malicious instructions are placed in documents, web pages, emails, or other content the agent retrieves, is the most under-defended attack class in production today. INP-02 requires that retrieved content be processed in a trust boundary that prevents it from issuing commands to the agent. Detection rates and false-positive rates are measured.

(Critical)A Critical failure precludes HI-AAF Certification regardless of the maturity level achieved on any other control.

Table INP-02.1 · Maturity criteria · v.1.3

L1 to L5 · the lowest level in scope caps the agent
L1Ad hoc

Controls exist informally; documentation is incomplete; no consistent review.

L2Documented

Controls are written down; ownership is assigned; review cadence is defined.

L3Operated

Controls are followed in practice; evidence is collected; deviations are tracked.

All retrieval paths apply trust boundary tagging; sampling-based human review of flagged retrievals is in place; injection-attempt rate is reported quarterly with trend analysis.

L4Measured

Control effectiveness is measured against documented thresholds; trends are reported.

L5Continuously Improved

Controls evolve based on incident learning; maturity gains are evidenced over time.

The v1.3 edition publishes a control-specific criterion at L3 (Operated). The other levels apply the general ladder to this control; see the maturity ladder.

Evidence an assessor asks for

  1. E.1

    All retrieval paths apply trust boundary tagging.

  2. E.2

    Sampling-based human review of flagged retrievals is in place.

  3. E.3

    Injection-attempt rate is reported quarterly with trend analysis.

Table INP-02.2 · Framework mappings

7 of 7 frameworks carry a control-level reference
NIST AI RMFMEASURE 2.7, MEASURE 2.8NIST AI Risk Management Framework 1.0
ISO/IEC 42001A.8.2ISO/IEC 42001:2023 · Artificial intelligence management system
OWASP LLM Top 10LLM01OWASP Top 10 for Large Language Model Applications
SOC 2 (TSC)CC7.1, CC7.2AICPA Trust Services Criteria for SOC 2 Type II
EU AI ActArt. 15(4)EU AI Act · Regulation (EU) 2024/1689
MITRE ATLASInitial AccessMITRE ATLAS · Adversarial Threat Landscape for AI Systems
SingaporeMAIGF Security, AI Verify Security, AI Verify RobustnessSingapore Model AI Governance Framework / AI Verify / PDPA

Mappings are directional: meeting this control evidences but does not by itself satisfy the external requirement. A middle dot means no control-level reference is published at this edition; see the crosswalk.

Related controls and terms

Cite this control

Human Intelligence. HI-AAF v1.3, INP-02 Indirect prompt injection defense. Public review edition, July 2026. https://humanintel.net/standard/inp/inp-02

Edition v.1.3 · July 2026 · Public review · Markdown · PDF

https://humanintel.net/standard/inp/inp-02

Notice

HI-AAF v1.3 is an independent framework published by Human Intelligence. It is not affiliated with NIST, ISO, AICPA, or any government or accreditation body. The framework is offered openly for review during the current draft cycle.