Skip to content
Human Intelligence seal
Human Intelligence
§ I · Domain OUT · Control 2 of 16
Control
OUT-02
Edition
v.1.3
Status
Public review

OUT · Output Integrity & Supply Chain

OUT-02Content safety filters

Content safety filters are applied to outputs, covering harmful content, harassment, illegal content, and other categories defined in the Behavior Charter.

Outputs are passed through safety filters appropriate to the deployment context. Filters cover harmful content, harassment, illegal content, and any additional categories defined in the agent's Behavior Charter. Filter configuration is documented, and filter effectiveness is measured. False negatives are treated as findings; false positives are tracked and tuned.

Table OUT-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.

Safety filters are active on all output paths; filter categories match the Behavior Charter; filter effectiveness is measured; false-negative incidents are tracked through remediation.

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

    Safety filters are active on all output paths.

  2. E.2

    Filter categories match the Behavior Charter.

  3. E.3

    Filter effectiveness is measured.

  4. E.4

    False-negative incidents are tracked through remediation.

Table OUT-02.2 · Framework mappings

5 of 7 frameworks carry a control-level reference
NIST AI RMFMEASURE 2.6NIST AI Risk Management Framework 1.0
ISO/IEC 42001·ISO/IEC 42001:2023 · Artificial intelligence management system
OWASP LLM Top 10LLM02OWASP Top 10 for Large Language Model Applications
SOC 2 (TSC)PI1.3AICPA Trust Services Criteria for SOC 2 Type II
EU AI ActArt. 15(3)EU AI Act · Regulation (EU) 2024/1689
MITRE ATLAS·MITRE ATLAS · Adversarial Threat Landscape for AI Systems
SingaporeAI Verify SafetySingapore 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.

Cite this control

Human Intelligence. HI-AAF v1.3, OUT-02 Content safety filters. Public review edition, July 2026. https://humanintel.net/standard/out/out-02

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

https://humanintel.net/standard/out/out-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.