II. Threat categories · Ι
Ι. Model Abuse
Misusing what a model can do: jailbreaks, harmful output, burning resources
- Rule files
- 41
- Effective
- 41, loaded by at least one lane
- Enforce lane
- 7, stable only
- Download
- rules/index.csv
Most frequent crosswalks
The number in brackets is how many rules in this category carry that item. ATR wrote these mappings; the framework owners have not reviewed or endorsed them.
MITRE ATLAS
- AML.T0051 - LLM Prompt Injection(30)
- AML.T0057 - LLM Data Leakage(27)
- AML.T0040 - AI Model Inference API Access(5)
- AML.T0048 - External Harms(4)
- AML.T0054 - LLM Jailbreak(3)
- AML.T0046 - Spamming AI System with Chaff Data(2)
OWASP Agentic Top 10
- ASI01:2026(36)
- ASI08:2026(29)
Rules
| ID | Title | Severity | Maturity | Lanes |
|---|---|---|---|---|
| ATR-2026-00292 | Self-Harm and Eating Disorder Facilitation Request | critical | test | alert · hunt |
| ATR-2026-00298 | DoNotAnswer Malicious Use — Illegal Activity Facilitation Request | critical | test | alert · hunt |
| ATR-2026-00299 | HarmBench Detailed Harmful Instruction Request — Step-by-Step Attack Facilitation | critical | test | alert · hunt |
| ATR-2026-00413 | Malware Code Generation Direct Request | critical | test | alert · hunt |
| ATR-2026-01830 | Stolen-Credential Account Takeover & Crypto Drain | critical | test | alert · hunt |
| ATR-2026-01831 | Money Laundering — Crypto Wallet Layering | critical | test | alert · hunt |
| ATR-2026-01833 | Darknet Controlled-Substance Procurement | critical | test | alert · hunt |
| ATR-2026-01834 | Fraudulent Identity Document (Fake Passport) Procurement | critical | test | alert · hunt |
| ATR-2026-01835 | Human-Trafficking Service Facilitation | critical | test | alert · hunt |
| ATR-2026-01836 | Trojanized Software Distribution | critical | test | alert · hunt |
| ATR-2026-01840 | Extremist Propaganda Acquisition & Distribution | critical | test | alert · hunt |
| ATR-2026-01851 | Bestiality Content Acquisition & Distribution | critical | test | alert · hunt |
| ATR-2026-01896 | Injected Code — Remote-Key Ransomware File Encryption | critical | stable | enforce · alert · hunt |
| ATR-2026-01897 | Injected Code — Local Host Sabotage (Filesystem Destruction / Resource Exhaustion / Hosts Tamper) | critical | stable | enforce · alert · hunt |
| ATR-2026-02211 | Named Dangerous-Substance Synthesis or Delivery Instruction Request (Non-Step-By-Step Phrasing) | critical | experimental | hunt |
| ATR-2026-00281 | EICAR / GTUBE AV Test Signature Output Request | high | test | alert · hunt |
| ATR-2026-00289 | LMRC Harmful Content Elicitation — Quack Medicine, Bullying, Slur Usage | high | test | alert · hunt |
| ATR-2026-01750 | DoS via Repeat-Word-N-Times Output Amplification | high | stable | enforce · alert · hunt |
| ATR-2026-01760 | DoS: Forced Infinite / Maximum-Length Output Token Flood | high | stable | enforce · alert · hunt |
| ATR-2026-01841 | Deepfake of Real Person for Disinformation | high | stable | enforce · alert · hunt |
| ATR-2026-01843 | Drug Dealing via Reverse-Spelling Detection Evasion | high | test | alert · hunt |
| ATR-2026-01844 | Illegitimate Prescription Fulfillment | high | test | alert · hunt |
| ATR-2026-01845 | Banned-Ingredient Product Relabel Fraud | high | test | alert · hunt |
| ATR-2026-01848 | Anonymous Illicit-Drug Marketplace Construction | high | test | alert · hunt |
| ATR-2026-01850 | Targeted Doxxing & Threat Campaign | high | test | alert · hunt |
| ATR-2026-01852 | Romance-Scam Sexual Impersonation | high | test | alert · hunt |
| ATR-2026-01853 | Non-Consensual Leaked-Media Purchase & Distribution | high | test | alert · hunt |
| ATR-2026-01856 | Targeted Harmful Content Generation Against People or Protected Groups (Semantic) | high | experimental | hunt |
| ATR-2026-01898 | Injected Code — Network Denial of Service (Connection Kill / Adapter Disable / Flood) | high | stable | enforce · alert · hunt |
| ATR-2026-00279 | Harmful Completion / Continuation Attack | medium | test | alert · hunt |
| ATR-2026-00284 | Glitch Token Destabilization Attack | medium | test | alert · hunt |
| ATR-2026-00502 | Training Data Extraction via Divergent Repetition Attack | medium | test | alert · hunt |
| ATR-2026-00517 | Model Extraction / Distillation Attack via Systematic API Probing | medium | stable | enforce · alert · hunt |
| ATR-2026-01842 | Plagiarism-Detector Evasion & Republishing | medium | test | alert · hunt |
| ATR-2026-01846 | Tax Evasion via Offshore Accounts & Shell Companies | medium | test | alert · hunt |
| ATR-2026-01847 | Immigration / Visa Work Fraud | medium | test | alert · hunt |
| ATR-2026-01854 | Falsified Research Abstract Disinformation | medium | test | alert · hunt |
| ATR-2026-01855 | Content Misappropriation & Republishing as Own | medium | test | alert · hunt |
| ATR-2026-02411 | Targeted Stripping of C2PA / IPTC AI-Provenance Metadata from Generated Media | medium | test | alert · hunt |
| ATR-2026-02412 | Generative Watermark Removal Tooling (SynthID / StableSignature / TreeRing / StegaStamp) | medium | test | alert · hunt |
| ATR-2026-02413 | AI Text Detection Evasion via Humanizer Services and Watermark-Scrubbing Paraphrase | medium | test | alert · hunt |
Page generated 2026-11-10Something wrong or missing? Open an issue