Skip to content
Human Intelligence seal
Human Intelligence
§ I · Domain MAS · Control 7 of 9
Control
MAS-07
Edition
v.1.3
Status
Public review

MAS · Multi-Agent Systems

MAS-07Aggregate blast-radius caps

Blast-radius limits under ACT-06 are evaluated across the entire chain, not only per-agent. Aggregate caps prevent a chain of individually in-bounds actions from producing an out-of-bounds combined effect.

Blast-radius limits under ACT-06 are evaluated across the entire chain, not only per-agent. Aggregate caps prevent a chain of individually in-bounds actions from producing an out-of-bounds combined effect (e.g., many small sub-agent transactions summing to an unauthorized total). This control addresses the emergent risk that arises when per-agent limits are met but the aggregate exceeds acceptable bounds.

Table MAS-07.1 · 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.

Aggregate caps are defined and enforced for all multi-agent chains with blast-radius implications; cap values are documented; enforcement has been tested through adversarial assessment or production monitoring.

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

    Aggregate caps are defined and enforced for all multi-agent chains with blast-radius implications.

  2. E.2

    Cap values are documented.

  3. E.3

    Enforcement has been tested through adversarial assessment or production monitoring.

Table MAS-07.2 · Framework mappings

5 of 7 frameworks carry a control-level reference
NIST AI RMFMANAGE 3.2NIST AI Risk Management Framework 1.0
ISO/IEC 42001·ISO/IEC 42001:2023 · Artificial intelligence management system
OWASP LLM Top 10·OWASP Top 10 for Large Language Model Applications
SOC 2 (TSC)CC6.3, CC8.1AICPA Trust Services Criteria for SOC 2 Type II
EU AI ActArt. 14(4), Art. 25(1)EU AI Act · Regulation (EU) 2024/1689
MITRE ATLASImpactMITRE ATLAS · Adversarial Threat Landscape for AI Systems
SingaporeMAIGF AccountabilitySingapore 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-07 Aggregate blast-radius caps. Public review edition, July 2026. https://humanintel.net/standard/mas/mas-07

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

https://humanintel.net/standard/mas/mas-07

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.