atlas_technique_lookup
Retrieve detailed information on MITRE ATLAS adversarial techniques targeting AI/ML systems, including prompt injection and model theft. Ideal for LLM red-teaming and threat analysis.
Instructions
Look up a MITRE ATLAS technique — the AI/ML adversarial attack catalog. ATLAS catalogues TTPs targeting machine learning systems: prompt injection, model evasion, training data poisoning, model theft, etc. Roughly 80% of ATLAS techniques are AI/ML-specific (no ATT&CK bridge); 20% mirror an enterprise ATT&CK technique via attack_reference_id — use that to pivot to D3FEND defenses (d3fend_defense_for_attack) and CVE search. Sub-techniques inherit tactics from the parent (inherited_tactics=true flag) when ATLAS upstream leaves them empty. Use this tool when the user asks about AI/ML threats, LLM red-teaming, or adversarial ML; for multiple techniques in one call (e.g. drilling into a case study's techniques_used), prefer bulk_atlas_technique_lookup. Returns 404 when the id is not in the synced ATLAS catalog. Free: 30/hr, Pro: 500/hr. Returns {technique_id, name, description, tactics, inherited_tactics, maturity (demonstrated|feasible|realized), attack_reference_id, attack_reference_url, subtechnique_of, created_date, modified_date, next_calls}.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| technique_id | Yes | MITRE ATLAS technique id, format 'AML.T####' or 'AML.T####.###' for sub-techniques (e.g. 'AML.T0000', 'AML.T0051' LLM Prompt Injection, 'AML.T0000.000'). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |