Skip to content
Human Intelligence seal
Human Intelligence
§ I · Domain MAS · Control 2 of 9
Control
MAS-02
Edition
v.1.3
Status
Public review

MAS · Multi-Agent Systems · Critical

MAS-02Agent-to-agent authentication

Every agent-to-agent invocation is authenticated using credentials issued to the calling agent's non-human identity. Authorization for cross-agent calls follows the principle of least privilege and is enforced at the runtime layer.

Every agent-to-agent invocation is authenticated using credentials issued to the calling agent's non-human identity (IAM-01). Authorization for cross-agent calls follows the principle of least privilege (IAM-03) and is enforced at the runtime layer, not solely in agent prompts or instructions. This control prevents unauthorized agent-to-agent communication and ensures that every cross-agent call is attributable.

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

Table MAS-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.

All agent-to-agent invocations are authenticated; authorization follows least privilege; enforcement is at the runtime layer; authentication failures are logged and reviewed.

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 agent-to-agent invocations are authenticated.

  2. E.2

    Authorization follows least privilege.

  3. E.3

    Enforcement is at the runtime layer.

  4. E.4

    Authentication failures are logged and reviewed.

Table MAS-02.2 · Framework mappings

7 of 7 frameworks carry a control-level reference
NIST AI RMFMANAGE 2.1NIST AI Risk Management Framework 1.0
ISO/IEC 42001A.8.4ISO/IEC 42001:2023 · Artificial intelligence management system
OWASP LLM Top 10LLM08OWASP Top 10 for Large Language Model Applications
SOC 2 (TSC)CC6.3AICPA Trust Services Criteria for SOC 2 Type II
EU AI ActArt. 25(1), Art. 14(4)EU AI Act · Regulation (EU) 2024/1689
MITRE ATLASExecutionMITRE ATLAS · Adversarial Threat Landscape for AI Systems
SingaporeMAIGF Accountability, 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, MAS-02 Agent-to-agent authentication. Public review edition, July 2026. https://humanintel.net/standard/mas/mas-02

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

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