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

SPC · Agent Specification & Pre-Deployment Assurance · Critical

SPC-03Adversarial assessment

An adversarial assessment (red team) is performed prior to initial deployment and after any material change. Minimum coverage: direct and indirect prompt injection, tool misuse, data exfiltration, role hijacking, jailbreak resistance, memory poisoning, and multi-agent escalation paths.

Red-team testing covers the full adversarial surface: direct and indirect prompt injection, tool misuse, data exfiltration paths, role hijacking, jailbreak resistance, memory poisoning (see INP-09), and where applicable, multi-agent escalation paths (see Domain 9). Findings are triaged, remediated or formally risk-accepted with executive sign-off, and the assessment is re-executed after material changes.

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

Table SPC-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.

Red team assessment report exists for every production agent; findings have been triaged and dispositioned; the assessment has been re-executed within the documented cadence or after the most recent material change.

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

    Red team assessment report exists for every production agent.

  2. E.2

    Findings have been triaged and dispositioned.

  3. E.3

    The assessment has been re-executed within the documented cadence or after the most recent material change.

Table SPC-03.2 · Framework mappings

7 of 7 frameworks carry a control-level reference
NIST AI RMFMEASURE 2.7, MEASURE 2.8NIST AI Risk Management Framework 1.0
ISO/IEC 42001A.6.2.5, 8.4ISO/IEC 42001:2023 · Artificial intelligence management system
OWASP LLM Top 10LLM06, LLM10OWASP Top 10 for Large Language Model Applications
SOC 2 (TSC)CC7.1AICPA Trust Services Criteria for SOC 2 Type II
EU AI ActArt. 9(6), Art. 15(4)EU AI Act · Regulation (EU) 2024/1689
MITRE ATLASReconnaissanceMITRE ATLAS · Adversarial Threat Landscape for AI Systems
SingaporeMAIGF Testing & Assurance, 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, SPC-03 Adversarial assessment. Public review edition, July 2026. https://humanintel.net/standard/spc/spc-03

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

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