TrojAI

The TrojAI + Wiz integration enables end-to-end AI security by combining Wiz’s AI asset discovery with TrojAI’s AI red teaming and runtime protection. TrojAI pulls AI models and endpoints from Wiz, performs automated red teaming to identify vulnerabilities such as prompt injection and data leakage, and pushes findings back into Wiz for centralized visibility and remediation. From here, TrojAI customers can build and enforce policy around their AI apps and agents. This allows security teams to move from discovery to testing and enforcement in a unified workflow, securing AI applications, agents, and models across their lifecycle.

Market Challenge

Enterprises are rapidly building and deploying AI apps and agents but lack visibility and security controls across their AI estate. As a result, security teams are looking for solutions to gain visibility into their growing AI infrastructure and address core AI risks such as prompt injection, data leakage, and AI toxicity, so that they can more confidently adopt, deploy, and innovate with AI.

Key Benefits of the Integration

• AI discovery – Get visibility into AI models through Wiz that can be seamlessly inventoried and tested in TrojAI

• Automated AI red teaming – Continuously identify vulnerabilities like prompt injection and data leakage across AI models and enrich Wiz with actionable risks insights

• End-to-end AI Security workflow – Connect AI asset discovery, risk prioritization, and attack path analysis in Wiz with TrojAI’s red teaming and protection, enabling teams to identify, validate, and remediate exploitable AI risks 

Better Together

Wiz provides leading visibility into cloud infrastructure and AI assets, while TrojAI delivers deep AI Security through red teaming and runtime protection. Together, they create a complete AI security lifecycle: Wiz discovers AI models and endpoints, and TrojAI assesses their behavior and enforces protections. Insights from TrojAI enrich the Wiz Security Graph, giving security teams a unified view of both infrastructure and AI risks. This partnership enables organizations to operationalize AI security, bringing together visibility, testing, and protection across their AI ecosystem.

As enterprises deploy AI agents and applications across their environments, they face new risks including prompt injection, data exfiltration, and toxic and unwanted content. Security teams often lack a clear inventory of AI assets and a way to assess their behavior.

With the TrojAI + Wiz integration, organizations first use Wiz to discover AI models and endpoints across their environment. TrojAI ingests this inventory and performs automated red teaming (TrojAI Detect) to identify AI risks and vulnerabilities. These findings are pushed back into Wiz, enriching the Wiz Security Graph with detailed risk insights, giving enterprises cloud context for these risks directly within Wiz.

TrojAI customers can then leverage TrojAI Defend to enforce runtime protections such as blocking malicious prompts, redacting sensitive data, or flagging suspicious activity. The result is a continuous, closed-loop AI security workflow that enables organizations to safely scale AI adoption while maintaining control over emerging risks.