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

INP · Input & Prompt Security

INP-10Retrieval and memory write authentication

Insertion paths into the agent's retrieval and memory layers are authenticated and authorized. Sources of retrievable content are documented. Adversarial insertion is tested as part of red-team coverage.

Write access to the agent's retrieval and memory layers, the paths by which content enters the corpus the agent can draw on, is authenticated and authorized. Sources of retrievable content are documented per DAT-10. Adversarial insertion is tested as part of red-team coverage to ensure that an attacker cannot plant content that will later influence agent behavior.

Table INP-10.1 · 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 write paths to retrieval and memory layers are authenticated; sources of retrievable content are documented; adversarial insertion testing has been performed within the documented cadence; unauthorized write attempts are logged.

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 write paths to retrieval and memory layers are authenticated.

  2. E.2

    Sources of retrievable content are documented.

  3. E.3

    Adversarial insertion testing has been performed within the documented cadence.

  4. E.4

    Unauthorized write attempts are logged.

Table INP-10.2 · Framework mappings

3 of 7 frameworks carry a control-level reference
NIST AI RMF·NIST AI Risk Management Framework 1.0
ISO/IEC 42001·ISO/IEC 42001:2023 · Artificial intelligence management system
OWASP LLM Top 10LLM07OWASP Top 10 for Large Language Model Applications
SOC 2 (TSC)·AICPA Trust Services Criteria for SOC 2 Type II
EU AI ActArt. 15(4)EU AI Act · Regulation (EU) 2024/1689
MITRE ATLAS·MITRE ATLAS · Adversarial Threat Landscape for AI Systems
SingaporeMAIGF Security, AI Verify SecuritySingapore 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-10 Retrieval and memory write authentication. Public review edition, July 2026. https://humanintel.net/standard/inp/inp-10

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

https://humanintel.net/standard/inp/inp-10

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.