SSG coverage claim · MITRE ATLAS-mapped
Browse AI-system risk by MITRE ATLAS
Browse the MITRE ATLAS v2026.08 tactic & technique taxonomy for AI systems, alongside SSG's own derived coverage tier for each technique — see the methodology note below for exactly what that tier does and does not claim.
Adversaries may use their access to an AI agent to invoke tools the agent has access to. LLMs are often connected to other services or resources via tools to increase their capabilities.
Tactics
Execution, Privilege Escalation, Lateral Movement
ATT&CK cross-reference
No Enterprise ATT&CK cross-reference.
ATLAS mitigations & SSG coverage
AML.M0020
Generative AI Guardrails
Partial
Guards the agent's actions at the tool boundary, not the model's token output
AML.M0021
Generative AI Guidelines
Not addressed
Prompt and system-instruction practice
AML.M0022
Generative AI Model Alignment
Not addressed
Model alignment training
AML.M0024
AI Telemetry Logging
Partial
Detective control: records every governed call; does not block it
AML.M0026
Privileged AI Agent Permissions Configuration
Enforced
Priority- and severity-scoped rules constrain privileged agent actions
AML.M0027
Single-User AI Agent Permissions Configuration
Partial
Per-project rule profiles; not a full multi-tenant identity system
AML.M0028
AI Agent Tools Permissions Configuration
Enforced
Per-tool ALLOW/DENY rules evaluated before the tool call executes
AML.M0029
Human In-the-Loop for AI Agent Actions
Enforced
ASK verdict halts the call until a human approves
AML.M0030
Restrict AI Agent Tool Invocation on Untrusted Data
Enforced
Content-conditioned rules gate tool invocation on untrusted input
AML.M0032
Segmentation of AI Agent Components
Partial
Rules fence paths and hosts; not process or network isolation
AML.M0033
Input and Output Validation for AI Agent Components
Enforced
Content matchers validate tool arguments before execution
AML.M0035
AI Red Team
Partial
SHAKEDOWN benchmark exercises containment; not a full red-team program
Methodology. Catalog: MITRE ATLAS v2026.08 (atlas.mitre.org).
Coverage tiers are derived from MITRE's own published mitigation↔technique mappings — never hand-assigned per technique.
SSG's claim is limited to which ATLAS mitigations it implements as controls; it does not claim to cover ATLAS techniques directly.
A tier records which SSG control exists for a MITRE-published mitigation — it is not a statement about outcome, and it is not a certification, an audit result, or an endorsement by MITRE.