Skip to content
Human Intelligence seal
Human Intelligence
§ I · Domain INP · Control 8 of 10
Control
INP-08
Edition
v.1.3
Status
Public review

INP · Input & Prompt Security

INP-08Untrusted content source handling

Untrusted content sources (emails, attachments, retrieved documents, web pages, embedded media) are handled as data; embedded instructions are not honored without verification.

Content from untrusted sources, emails, attachments, retrieved documents, web pages, embedded media, is treated as data, not as instruction. Any instructions embedded in such content are not honored without explicit verification through the trust boundary defined in INP-03. This control is the operational complement to INP-02's indirect injection defense.

Table INP-08.1 · 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 untrusted content sources are identified and documented; handling rules treat embedded instructions as data; the control is tested as part of adversarial assessment; no embedded instruction from an untrusted source has been executed without verification.

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 untrusted content sources are identified and documented.

  2. E.2

    Handling rules treat embedded instructions as data.

  3. E.3

    The control is tested as part of adversarial assessment.

  4. E.4

    No embedded instruction from an untrusted source has been executed without verification.

Table INP-08.2 · Framework mappings

4 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 10LLM01, LLM05OWASP 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 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-08 Untrusted content source handling. Public review edition, July 2026. https://humanintel.net/standard/inp/inp-08

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

https://humanintel.net/standard/inp/inp-08

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.