AInforce

Threat Framework Coverage

Built against the frameworks your security team already uses.

OWASP, MITRE ATLAS, and MITRE ATT&CK define the threat landscape for AI systems. Every AInforce module maps directly to these controls — so your security team has a coverage story they can defend.

9/10OWASP LLM Top 10Reference
11/12MITRE ATLASReference
8/10MITRE ATT&CKReference

28 of 32 threats addressed across all three frameworks. Partial coverage noted where detection is present but automated response is in development.

IDThreat / TacticModuleCoverage
LLM01:2025

Prompt Injection

Hundreds of injection variants tested per endpoint daily across direct and indirect attack surfaces. Auto-generated attack chains, scored and triaged.

Red Teaming
Covered
LLM02:2025

Sensitive Information Disclosure

Every AI interaction logged with automated data classification. PII, source code, secrets, and regulated data flagged in real time with identity attribution.

Observatory
Covered
LLM03:2025

Supply Chain

Model SBOM generation, cryptographic provenance verification, and dependency auditing across your entire AI stack — from base models to fine-tuned derivatives.

Supply Chain
Covered
LLM04:2025

Data and Model Poisoning

Vector DB poisoning alerts, behavioral baseline drift detection, and hash-verified model integrity checks catch tampering before it reaches production inference.

Supply Chain
Covered
LLM05:2025

Improper Output Handling

All LLM outputs inspected and classified before downstream consumption. Anomalous or policy-violating outputs flagged with full session context for review.

Observatory
Covered
LLM06:2025

Excessive Agency

Tool call interception validates every action against a declared permission scope. Privilege escalation attempts blocked; human-in-the-loop approval queue for high-risk actions.

Agent Security
Covered
LLM07:2025

System Prompt Leakage

Daily test suites probe every AI endpoint for system prompt extraction via direct elicitation, role-play bypass, and jailbreak variants.

Red Teaming
Covered
LLM08:2025

Vector and Embedding Weaknesses

Vector DB poisoning audits detect adversarial embeddings and data integrity violations in RAG pipelines. Baseline comparison surfaces drift over time.

Supply Chain
Covered
LLM09:2025

Misinformation

Behavioural anomaly detection surfaces unusual output patterns. Ground-truth factual verification is on the roadmap for domain-specific knowledge bases.

Observatory
Partial
LLM10:2025

Unbounded Consumption

Red Teaming runs token exhaustion and DoS variant suites daily. Agent Security enforces per-agent resource budgets and blocks runaway tool call chains.

Multiple
Covered
IDThreat / TacticModuleCoverage
AML.TA0001

Reconnaissance

Passive AI footprint mapping via DNS, certificate transparency, CSP headers, and ATS job board intelligence reveals your attack surface before adversaries do.

Scanner
Covered
AML.TA0002

Resource Development

Attack infrastructure simulation covers most tooling categories. Tracking of adversarial model development (shadow model training) is on the roadmap.

Red Teaming
Partial
AML.TA0003

Initial Access

Scanner identifies externally exposed AI endpoints. Agent Security enforces access controls at the runtime layer. Combined coverage of both external and internal access paths.

Multiple
Covered
AML.TA0004

Execution

OWASP LLM attack suites simulate adversarial execution paths daily — including prompt-injected code execution, tool call abuse, and agentic chain exploitation.

Red Teaming
Covered
AML.TA0005

Persistence

Cryptographic model integrity verification and behavioral baseline comparison detect unauthorized model modifications that would enable persistent attacker access.

Supply Chain
Covered
AML.TA0006

Privilege Escalation

Real-time privilege escalation detection blocks agents from acquiring permissions beyond their declared scope. Multi-step chain auditing catches escalation sequences.

Agent Security
Covered
AML.TA0007

Defense Evasion

Jailbreak, role-play bypass, and context-window manipulation test suites simulate evasion techniques. Continuously updated attack library tracks new evasion research.

Red Teaming
Covered
AML.TA0008

Discovery

External reconnaissance from the attacker's vantage point — enumerating your AI tools, inference endpoints, and SaaS integrations before an attacker does.

Scanner
Covered
AML.TA0009

Collection

Complete AI interaction logging with PII, code, and secrets classification. Every data element moving through an AI system is captured, labelled, and attributed to an identity.

Observatory
Covered
AML.TA0010

ML Attack Staging

Daily OWASP attack suite runs simulate full attack staging sequences — reconnaissance to exploit — against each AI endpoint in your environment.

Red Teaming
Covered
AML.TA0011

Exfiltration

Output inspection classifies every model response for sensitive data. Anomalous exfiltration patterns trigger alerts with the full session and identity context.

Observatory
Covered
AML.TA0012

Impact

High-risk agentic actions require human-in-the-loop approval before execution. Tool call blocking and rate enforcement stop downstream impact before it occurs.

Agent Security
Covered
IDThreat / TacticModuleCoverage
T1190

Exploit Public-Facing Application

AI endpoints treated as public-facing attack surfaces. Daily exploit suites test LLM APIs, agent endpoints, and RAG interfaces for injection, extraction, and bypass vulnerabilities.

Red Teaming
Covered
T1059

Command and Scripting Interpreter (via AI agents)

Tool call validation intercepts every code execution request issued by an AI agent. Declared-scope enforcement blocks unapproved interpreter access before execution.

Agent Security
Covered
T1195

Supply Chain Compromise

Model SBOM tracking, cryptographic provenance chains, and hash-verified integrity checks cover the AI model supply chain from pre-trained base to fine-tuned production version.

Supply Chain
Covered
T1552

Unsecured Credentials (in AI prompts and outputs)

Real-time secrets detection in every AI interaction. Credentials, API keys, and tokens embedded in prompts or returned in model outputs are flagged immediately.

Observatory
Covered
T1213

Data from Information Repositories (RAG exfiltration)

Supply Chain audits RAG pipeline integrity. Observatory classifies data moving through retrieval-augmented queries and detects over-permissive retrieval patterns.

Multiple
Covered
T1565

Data Manipulation (model and vector poisoning)

Vector DB poisoning audit and model behavioral drift detection identify adversarial data manipulation before it affects production inference or downstream decisions.

Supply Chain
Covered
T1048

Exfiltration Over Alternative Protocol (via AI APIs)

AI API interactions logged and inspected for anomalous data volumes and sensitive content. Exfiltration via model outputs detected regardless of the API transport.

Observatory
Covered
T1499

Endpoint Denial of Service (via AI agents)

Agent Security enforces per-agent compute and call budgets. Red Teaming runs token exhaustion and recursive tool call DoS simulations against every AI endpoint.

Multiple
Covered
T1078

Valid Accounts (AI-assisted credential theft)

Behavioural anomaly detection flags account usage patterns inconsistent with the established baseline. Full identity provider integration for anomalous login correlation is on the roadmap.

Observatory
Partial
T1566

Phishing (AI-enhanced spearphishing)

Employee AI tool usage patterns surfaced for policy enforcement. Detection of AI-generated phishing content in outbound interactions is on the roadmap.

Observatory
Partial

Coverage legend

Covered — detection and automated response in productionPartial — detection present, automated response in developmentRoadmap — committed for a future release

Coverage is self-attested and reflects the capabilities of the Monitor and Enforce tiers. The Free tier (AI Risk Scanner) covers OWASP LLM Top 10 external surface indicators only. ATT&CK technique selection focuses on AI-specific abuse paths — the full ATT&CK matrix contains 200+ techniques; contact us for a complete mapping.

Full security posture →

NIST AI RMF, ISO 27001, SOC 2, GDPR, EU AI Act