Authentic ATLAS coverage, technique by technique.

RAIDER's catalog uses real MITRE ATLAS identifiers (v5.6.0) — AML.T* techniques under authentic AML.TA* tactics, with AML.M* mitigations and OWASP LLM Top 10 cross-references. It spans direct/indirect/triggered prompt injection, system-prompt & RAG data extraction, credential harvesting, and corpus poisoning & false-entry injection. Below is the full set of 43 techniques and how each is exercised.

43ATLAS techniques

35auto-executable

10probe engines

8assessment-only

Coverage legend. auto executed via the LLM-chat / attacker-judge path · engine a consent-gated probe engine (artifact scan · recon · RAG poison / inject / read) · assessment checklist / evidence review. All identifiers are authentic — cross-check at atlas.mitre.org.

Reconnaissance · AML.TA0002

Technique	Name	Coverage	OWASP
`AML.T0006`	Active Scanning	recon	—
`AML.T0064`	Gather RAG-Indexed Targets	RAG read	LLM08

Resource Development · AML.TA0003

Technique	Name	Coverage	OWASP
`AML.T0065`	LLM Prompt Crafting	auto	LLM01

Initial Access · AML.TA0004

Technique	Name	Coverage	OWASP
`AML.T0052.000`	Phishing: Spearphishing via Social Engineering LLM	auto	LLM09
`AML.T0010.002`	AI Supply Chain Compromise: Data	artifact scan	LLM03
`AML.T0010.003`	AI Supply Chain Compromise: Model	artifact scan	LLM03
`AML.T0052`	Phishing	assessment	—

Execution · AML.TA0005

Technique	Name	Coverage	OWASP
`AML.T0051.000`	LLM Prompt Injection: Direct	auto	LLM01
`AML.T0051.001`	LLM Prompt Injection: Indirect	auto	LLM01
`AML.T0051.002`	LLM Prompt Injection: Triggered	auto	LLM01
`AML.T0053`	AI Agent Tool Invocation	auto	LLM06
`AML.T0011.000`	User Execution: Unsafe AI Artifacts	artifact scan	LLM03

Persistence · AML.TA0006

Technique	Name	Coverage	OWASP
`AML.T0061`	LLM Prompt Self-Replication	auto	LLM01
`AML.T0070`	RAG Poisoning	RAG poison	LLM08
`AML.T0018.000`	Manipulate AI Model: Poison AI Model	assessment	LLM04
`AML.T0020`	Poison Training Data	assessment	LLM04

Privilege Escalation · AML.TA0012

Technique	Name	Coverage	OWASP
`AML.T0054`	LLM Jailbreak	auto	LLM01

Defense Evasion · AML.TA0007

Technique	Name	Coverage	OWASP
`AML.T0067`	LLM Trusted Output Components Manipulation	auto	LLM05
`AML.T0068`	LLM Prompt Obfuscation	auto	LLM01
`AML.T0092`	Manipulate User LLM Chat History	auto	LLM01
`AML.T0094`	Delay Execution of LLM Instructions	auto	LLM01
`AML.T0071`	False RAG Entry Injection	RAG inject	LLM08
`AML.T0015`	Evade AI Model	assessment	—

Credential Access · AML.TA0013

Technique	Name	Coverage	OWASP
`AML.T0082`	RAG Credential Harvesting	RAG read	LLM02

Discovery · AML.TA0008

Technique	Name	Coverage	OWASP
`AML.T0062`	Discover LLM Hallucinations	auto	LLM09
`AML.T0069`	Discover LLM System Information	auto	LLM07
`AML.T0069.000`	Discover LLM System Information: Special Character Sets	auto	LLM07
`AML.T0069.001`	Discover LLM System Information: System Instruction Keywords	auto	LLM07
`AML.T0069.002`	Discover LLM System Information: System Prompt	auto	LLM07
`AML.T0007`	Discover AI Artifacts	recon	—

Lateral Movement · AML.TA0015

Technique	Name	Coverage	OWASP
`AML.T0052.000`	Phishing: Spearphishing via Social Engineering LLM (also Initial Access)	auto	LLM09

Collection · AML.TA0009

Technique	Name	Coverage	OWASP
`AML.T0085.000`	Data from AI Services: RAG Databases	RAG read	LLM02

AI Attack Staging · AML.TA0001

Technique	Name	Coverage	OWASP
`AML.T0088`	Generate Deepfakes	auto	LLM09
`AML.T0102`	Generate Malicious Commands	auto	LLM05
`AML.T0043`	Craft Adversarial Data	assessment	—

Exfiltration · AML.TA0010

Technique	Name	Coverage	OWASP
`AML.T0056`	Extract LLM System Prompt	auto	LLM07
`AML.T0057`	LLM Data Leakage	auto	LLM02
`AML.T0077`	LLM Response Rendering	auto	LLM02, LLM05
`AML.T0024.000`	Exfiltration via AI Inference API: Infer Training Data Membership	assessment	LLM02
`AML.T0024.001`	Exfiltration via AI Inference API: Invert AI Model	assessment	LLM02
`AML.T0024.002`	Exfiltration via AI Inference API: Extract AI Model	assessment	LLM02

Impact · AML.TA0011

Technique	Name	Coverage	OWASP
`AML.T0029`	Denial of AI Service	auto	LLM10
`AML.T0034.001`	Cost Harvesting: Resource-Intensive Queries	auto	LLM10
`AML.T0048`	External Harms	auto	LLM09, LLM05

Every finding carries its ATLAS technique, tactic, and mitigation IDs plus OWASP references into the chain-of-evidence report. See the Documentation and API reference, or request a demo.