Skip to content
Human Intelligence seal
Human Intelligence
§ I · Domain MAS · Control 3 of 9
Control
MAS-03
Edition
v.1.3
Status
Public review

MAS · Multi-Agent Systems · Critical

MAS-03Confirmation binding across chains

User-confirmation requirements under INP-03 and pre-execution-review requirements under ACT-03 bind across multi-agent chains. A confirmation given to one agent does not authorize a downstream agent to take an unconfirmed consequential action.

User-confirmation requirements under INP-03 and pre-execution-review requirements under ACT-03 bind across multi-agent chains. A confirmation given to one agent does not authorize a downstream or sub-agent to take a separate consequential action on the user's behalf. The originating user's scope travels with the request and constrains every hop. This prevents the common pattern where a downstream agent assumes inherited authority.

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

Table MAS-03.1 · 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.

Confirmation binding is enforced across all multi-agent chains; the control has been tested through adversarial assessment; no downstream agent has taken an unconfirmed consequential action in the review period.

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

    Confirmation binding is enforced across all multi-agent chains.

  2. E.2

    The control has been tested through adversarial assessment.

  3. E.3

    No downstream agent has taken an unconfirmed consequential action in the review period.

Table MAS-03.2 · Framework mappings

6 of 7 frameworks carry a control-level reference
NIST AI RMFMANAGE 2.3NIST AI Risk Management Framework 1.0
ISO/IEC 42001·ISO/IEC 42001:2023 · Artificial intelligence management system
OWASP LLM Top 10LLM06OWASP Top 10 for Large Language Model Applications
SOC 2 (TSC)CC6.3AICPA Trust Services Criteria for SOC 2 Type II
EU AI ActArt. 14(4)EU AI Act · Regulation (EU) 2024/1689
MITRE ATLASExecutionMITRE ATLAS · Adversarial Threat Landscape for AI Systems
SingaporeMAIGF Accountability, AI Verify Human Agency & OversightSingapore 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, MAS-03 Confirmation binding across chains. Public review edition, July 2026. https://humanintel.net/standard/mas/mas-03

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

https://humanintel.net/standard/mas/mas-03

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.