AuditaAI
Back to vendors

AI security vendor

Protect AI

Operating organization under Palo Alto Networks

Official website

2

Offerings

2

Reviewed claims

4

Capabilities

Domains

Data and PrivacyModel and ValidationRuntime ProtectionSupply Chain and Integrity

Actions

PREVENTDETECTPOSTUREAUDIT

Offerings

Open an offering for reviewed behavior and evidence

Protect AI · project

LLM Guard

1 claims+

Open-source LLM security scanner and guardrails library for real-time prompt sanitization, jailbreak mitigation, and output data leakage prevention.

Official source
Prompt and Response GuardrailsPrompt and Response DLP
PREVENTDETECT

LLM Guard inspects, sanitizes, and evaluates LLM prompts and model completions against prompt injection, jailbreaks, and sensitive data leakage.

Source

Protect AI · project

ModelScan

1 claims+

Open-source ML model security scanner that inspects serialized model artifacts (PyTorch, Pickle, Keras, SavedModel) for arbitrary code execution exploits and malicious payloads.

Official source
Model Security TestingDependency Integrity
POSTUREAUDIT

ModelScan statically analyzes serialized ML model files (PyTorch, Pickle, SavedModel, Keras) to detect embedded code execution exploits and malicious payload injections.

Source