VORTEX

Cloud AI Infrastructure Exploitation

Your models live in the cloud. VORTEX owns the cloud. Service discovery, misconfiguration exploitation, model theft, data exfiltration, privilege escalation, and persistent cloud access — weaponised for authorised red team engagements.

7
Subsystems
36
Techniques
245
Tests
View Documentation GitHub

Own the Infrastructure, Own the Models

VORTEX targets the cloud infrastructure that AI systems run on. Every model endpoint, every GPU cluster, every model registry, every inference API — running on cloud infrastructure that was never designed for AI-specific threats. VORTEX finds the gaps between cloud security and AI security.

01

DISCOVER

SERVICE DISCOVERY

Enumerate cloud AI services. Model endpoint discovery. GPU cluster identification. Model registry scanning. Inference API mapping. SageMaker, Vertex AI, Azure ML detection.

02

CONFIG

MISCONFIGURATION

Cloud AI misconfiguration exploitation. Open model endpoints. Exposed training data. Permissive IAM policies. Unprotected model registries. Public inference APIs.

03

THEFT

MODEL THEFT

Model extraction via cloud access. Weight exfiltration. Architecture reconstruction. API-based model stealing. Side-channel model extraction.

04

EXFIL

DATA EXFILTRATION

Training data extraction. Inference data capture. Model input/output logging exploitation. Cloud storage enumeration. Data pipeline interception.

05

PRIVESC

PRIVILEGE ESCALATION

Cloud AI privilege escalation. IAM role chaining. Service account exploitation. Cross-service pivoting. GPU node escalation. Container breakout.

06

PERSIST

CLOUD PERSISTENCE

Maintain access to cloud AI infrastructure. Model backdoor injection. Pipeline persistence. Scheduled task manipulation. Container image poisoning.

07

ANTIDOTE

MANDATORY RESTORE

Baseline capture before any engagement. Cloud configuration snapshot. IAM policy audit. Signed restoration certificate.

UNLEASHED Gate

Standard mode detects. UNLEASHED exploits. Ed25519 crypto. Dual-gate safety. One operator.

Detection

Maps cloud AI attack surfaces. Identifies misconfigurations and exposed endpoints. No exploitation. Reports only.

Dry Run

Plans full cloud exploitation campaigns. Shows exactly what would work. Ed25519 required. No execution.

Live Execution

Cryptographic override. Private key controlled. One operator. Founder's machine only.

THIS TOOL IS FOR AUTHORISED SECURITY TESTING ONLY. EVERY EXECUTION IS SIGNED AND LOGGED.

36
Techniques
245
Tests
7
Subsystems
49,301
Ecosystem Tests
Available On

Security Distros & Package Managers

Kali Linux
.deb package
Parrot OS
.deb package
BlackArch
PKGBUILD
REMnux
.deb package
Tsurugi
.deb package
PyPI
pip install

Your Models Live in the Cloud. VORTEX Owns the Cloud.

36 techniques. 7 subsystems. Service discovery. Model theft. Privilege escalation. The tool that proves your cloud AI infrastructure isn't safe.