Explore the Complete Risk Framework
View Detailed AI Risk Categories →Understanding the Landscape of AI Risks
Enkrypt AI organises AI risk into 8 top-level categories containing 35 sub-categories. This taxonomy is the shared vocabulary across the platform: it is what you scope a Red Team run with, and it is how results are reported back to you.These IDs are the ones you use in the
risk_categories field of a Red Team payload. For
configuration detail see the
Risk Category Catalog.The eight categories
Safety & Harm — safety_harm
Safety & Harm — safety_harm
Content that materially harms people or enables physical harm, irrespective of legality.
Privacy & Data Protection — privacy_data_protection
Privacy & Data Protection — privacy_data_protection
Disclosure, inference, or aggregation of personal data — memorisation, cross-session
leakage, redaction bypass, re-identification, and unsafe data egress.
Security & Fraud — security_fraud
Security & Fraud — security_fraud
Material uplift to financial fraud, identity theft, credential theft, social engineering,
malware or exploit development, or attacks against third-party systems.
Bias, Fairness & Ethical Harm — bias_fairness_ethical_harm
Bias, Fairness & Ethical Harm — bias_fairness_ethical_harm
Dignitary, allocative, or representational harm — stereotyping, identity-based attacks,
and biased decisions across protected attributes.
Legal & IP Liability — legal_ip_liability
Legal & IP Liability — legal_ip_liability
Content creating statutory, contractual, or intellectual-property exposure.
Brand, Reputation & Trust — brand_reputation_trust
Brand, Reputation & Trust — brand_reputation_trust
Damage to the deploying brand’s standing — off-voice output, fabricated brand claims,
competitor disparagement, and content the brand would never endorse.
Product Misuse & Abuse — product_misuse_abuse
Product Misuse & Abuse — product_misuse_abuse
Users pushing your system outside its intended operating scope — out-of-domain
hijacking, role override, and resource abuse.
Performance, Reliability & Quality — performance_reliability_quality
Performance, Reliability & Quality — performance_reliability_quality
Quality failures under non-malicious load — incorrect, inconsistent, or ill-formed
output.
Compliance frameworks
The same taxonomy underpins compliance reporting. Each framework’s controls map onto the categories and sub-categories above, so a single run can be re-expressed against any of them.Risk Assessment Framework
Detection Capabilities
- Real-time Analysis — instant detection across risk categories
- Context Understanding — nuanced interpretation grounded in your system description
- Multi-language Support — detection and adversarial testing across languages
- Multi-modal Coverage — text, image and audio inputs
Mitigation Strategies
- Content Filtering — automatic blocking of harmful content via Guardrails
- Risk Scoring — attack success rate per category, sub-category and attack method
- Generated Remediation — hardened system prompts and Guardrails policies derived from run results
- Compliance Reporting — results mapped onto the frameworks above for audit
Related
Risk Category Catalog
Full detail on what each category and sub-category tests for.
Red Team Quickstart
Scope a run against these categories and read the report.
Attack Methods
The 21 techniques used to probe each category.
Guardrails
Detect and block these risks at runtime.