Scope boundary

Owns signed, version-bound reference artifacts that document an AI system and quantify expected behavior under governed conditions. It creates and recalibrates trusted baselines but does not claim the system is attack-free or perform live detection and alerting.

Sub-techniques

• AID-M-003.001: Model Card & Datasheet Generation
• AID-M-003.002: General Predictive Performance & Operational Baselining
• AID-M-003.003: Explainability (XAI) Output Baselining
• AID-M-003.004: Agent Goal & Mission Baseline Integrity
• AID-M-003.005: Reconstruction-Error Baseline for Image/Media Anomaly Detection
• AID-M-003.006: Graph-Structured Model Behavioral Baselining
• AID-M-003.007: LLM Behavior & Prompt-Suite Baselining

Threat mappings

MITRE ATLAS

• AML.T0081 Modify AI Agent Configuration

MAESTRO

• Lack of Explainability in Security AI Agents (L6)
• Agent Goal Manipulation (L7)
• Inaccurate Agent Capability Description (L7)

OWASP LLM Top 10 2026

• N/A

OWASP ML Top 10 2023

• N/A

OWASP Top 10 for Agentic Applications 2026

• N/A

NIST Adversarial Machine Learning 2025

• N/A

Cisco Integrated AI Security and Safety Framework

• AITech-1.1 Direct Prompt Injection and Jailbreak (Prompt-based Manipulation)
• AITech-5.2 Configuration Persistence
• AITech-8.2 Data Exfiltration / Exposure
• AITech-8.3 Information Disclosure
• AITech-8.4 Prompt/Meta Extraction
• AISubtech-1.1.1 Instruction Manipulation
• AISubtech-5.2.1 Agent Profile Tampering
• AISubtech-8.3.3 Personally Identifiable Information Exposure
• AISubtech-8.3.4 Payment Card Industry Data Exposure
• AISubtech-8.4.1 System LLM Prompt Leakage

Google Secure AI Framework 2.0 - Risks

• N/A

Databricks AI Security Framework 3.0

• Algorithms 5.1: Lack of tracking and reproducibility of experiments
• Evaluation 6.2: Insufficient evaluation data
• Evaluation 6.3: Lack of Interpretability and Explainability
• Agents - Core 13.6: Intent Breaking & Goal Manipulation