Skip to main content
Tier 2 Engine

AI Security Static Engine

Deterministic static code analysis for AI/ML attack surface detection. AST-based scanning with 82+ core rules plus 5 specialized profiles for prompt injection, agent safety, data leakage, and tool abuse.

82+
Core Rules
14
Rule Families (R1-R14)
6
Scan Profiles
100%
Deterministic

What It Does

Static Code Analysis

Analyzes source code using AST (Abstract Syntax Tree) parsing to detect AI-specific vulnerabilities without executing code.

Prompt Injection Detection

Identifies user input reaching LLM prompts without validation (R1). Detects 15+ patterns including direct concatenation and template injection.

Data Leakage Prevention

Detects sensitive data exposure through LLM outputs, logging, and error messages (R7.1-R7.6). Tracks data flow from source to sink.

Compliance Evidence

Maps findings to SOC2, GDPR, HIPAA, ISO27001, and OWASP LLM Top 10. Generates cryptographically signed artifacts for auditors.

What It Doesn't Do

Important limitations to understand:

No Runtime Testing

Cannot detect vulnerabilities that only appear at runtime. Use Runtime Engine for that.

No AI/ML Detection

Uses deterministic pattern matching, not machine learning. 100% reproducible results.

No Code Execution

Analyzes code structure only. Never runs your code or makes external requests.

No Certification

Provides evidence for auditors. Does not certify compliance or security.

Quick Start (5 minutes)

1

Connect Your Repository

Navigate to Dashboard → AI Security → New Scan and enter your GitHub repository URL.

https://github.com/your-org/your-ai-app
2

Run Scan

Click "Start Scan". The engine will clone your repo (ephemeral), analyze it, and delete the clone.

Privacy: Repository is cloned to /tmp/scan_[timestamp] and deleted immediately after scan. No code is stored.

3

Review Findings

View findings categorized by severity (Critical, High, Medium, Low) with fix recommendations.

Try Interactive Demo

Core Rule Families (R1-R14)

R1CRITICAL

Prompt Injection

User input reaches system/developer prompt without validation

R2CRITICAL

Tool Abuse

Model output triggers privileged action (PythonREPL, Shell, eval/exec)

R3HIGH

Tool Argument Validation

Tool arguments lack validation or sanitization

R4HIGH

RAG Poisoning

Indirect prompt injection via unvalidated retrieval documents

R5CRITICAL

Auth / Access Control

Missing authentication on AI entrypoints

R6HIGH

Multi-Tenant Isolation

Missing tenant scoping on AI-accessible data

R6.1-R6.10HIGH

Agent Safety Suite

Agent loops, memory, function calling, parallel execution, streaming, multi-modal input

R7HIGH

Secrets Exposure

Secrets flow to AI context, logs, or outbound channels

R8HIGH

SSRF / Egress Control

Outbound requests lack strict egress controls

R9HIGH

AI Control Stability

Non-deterministic AI on privileged execution paths

R10HIGH

Authorization / RBAC

Missing AI authorization boundary enforcement

R11HIGH

Output Validation

AI output lacks validation before downstream use

R12MEDIUM

Resource Protection

Missing rate limiting on AI endpoints

R13MEDIUM

Context Window Security

Context window overflow risk

R14HIGH

Model Confusion

Model confusion or parameter injection attacks

Specialized Scan Profiles

Profiles are additive — selecting multiple profiles merges their rule packs with deduplication. The DEFAULT profile is always included.

82rules

Default

R1-R14

Core AI security rules covering prompt injection, tool abuse, secrets, SSRF, agent safety, and more

7rules

Voice AI

VAI-

Telephony webhook security, STT input boundaries, session integrity, PII/recording compliance

12rules

Agentic Workflow

AGW-R

Agent loop safety, tool selection governance, action governance, state integrity, idempotency

10rules

Embedded SaaS

ESA-R

RBAC enforcement, context minimization, stored injection, feature gating, audit logging

8rules

Deep RAG

RAG-R

Retrieval scope, embedding access control, document provenance, embedding drift detection

45rules

AI-Assisted Dev

AIC-R

Supply chain integrity, IAM risk, license/IP contamination, testing enforcement, AI governance