Last updated at Tue, 03 Jun 2025 20:30:10 GMT

The rise of GenAI-powered applications – from internal copilots to customer-facing chatbots – is changing how businesses operate. While these tools drive innovation, they also introduce a fast moving, often invisible layer of risk.

Most traditional AppSec tools were never built to handle the unique threats of conversational AI interfaces. As attackers get savvier, security teams need the right kind of coverage.

That’s why we’re excited to introduce AI Attack Coverage in Exposure Command and InsightAppSec.

This release brings purpose built protection for AI driven applications into your existing AppSec workflows, so you can uncover vulnerabilities that legacy tools miss – and stop AI specific threats before they become business problems.

A new class of risk requires a new kind of coverage

As organizations embrace GenAI, they’re also expanding their attack surface – often without realizing it. LLMs (large language models) and AI integrations create new opportunities for attackers to exploit vulnerabilities like:

  • Prompt injection: Tricking the model into revealing sensitive data or bypassing security controls.
  • Plugin abuse: Misusing connected tools through AI interfaces.
  • Data leakage: Inadvertent exposure of sensitive information in responses.

The problem? These aren’t issues most scanners can detect, and manual reviews don’t scale. AI Attack Coverage addresses this gap head-on with capabilities designed to tackle the evolving threat landscape.

Built to secure what matters most

AI Attack Coverage in Exposure Command introduces a suite of enhancements that work seamlessly within your existing DevSecOps pipelines:

  • Smarter scanning for smarter apps: Our enhanced R7Crawler interacts with LLMs and chatbots in real-world ways – uncovering vulnerabilities traditional scanners can’t see.
  • Purpose built LLM testing: With 6 new attack modules, comprising 25+ new attack techniques, that will target six of the OWASP Top 10 for LLMs, we help you find prompt injection, improper output handling, and more.
  • AI aware validation: Reduce false positives with intelligent validation powered by AWS Nova Pro, so teams can focus on what’s real and actionable.
  • Developer first remediation: Features like Attack Replay and CI/CD integrations help teams fix faster – without slowing down releases​.


Complete visibility, from code to cloud

Exposure Command doesn’t stop at the app layer. With integrated telemetry from InsightCloudSec, you also get:

  • Full-stack visibility into where GenAI services live across your environment.
  • Automated enforcement of security best practices for AI/ML environments.
  • Unified context to prioritize what’s truly risky in your hybrid estate. ​

Get started with AI Attack Coverage

If you’re building with AI – or thinking about it – now’s the time to make sure your security strategy keeps up. AI Attack Coverage gives your team the visibility, context, and control to manage risk in a world where apps are getting smarter, and attackers are more adept at exploiting them.

Whether you’re an AppSec engineer, a risk leader, or a CISO trying to future-proof your security posture, Exposure Command brings it all together.

Learn More About Rapid7’s Exposure Command

Confidently identify and prioritize exposures from endpoint to cloud with full attack surface visibility and threat-aware risk context.