cyber.hendryadrian.com
Security News · wiz.io

Wiz Extends AI Application Security From Code to Runtime Remediation

· Original article ↗

Summary

Wiz says its platform will detect AI-specific risks in code, validate whether they are exploitable at runtime, trace findings to their code roots, and route fixes through developers’ workflows.

Key points

  • Wiz says its unified policy engine applies AI security checks across code, cloud, and runtime, with SAST rules mapped to OWASP’s LLM and agentic application guidance.
  • The platform scans code in developer workflows using the Wiz CLI and IDE extensions, alongside SAST, SCA, infrastructure-as-code, and secrets scanning.
  • Wiz says its Red Agent probes live application endpoints to validate whether detected weaknesses, such as SQL injection, are exploitable and exposed.
  • SAST links runtime findings back to the code-level cause so teams can identify where a risk was introduced.
  • Wiz’s Green Agent can generate context-based fixes and route remediation through developer workflows or an organization’s coding agent.
  • Wiz says dedicated skills and plugins for coding agents and AI-native IDEs are planned for a future release.

Article Details

Event Type
Product announcement expanding Wiz Code’s AI application security capabilities across development and runtime.
Impact
Wiz says the unified workflow detects AI-specific risks in code, validates whether vulnerabilities are exploitable at runtime, maps findings to their code-level causes, and supports remediation through the Green Agent or an organization’s coding agent. The article describes these capabilities but reports no specific customer incident or realized security impact.

Vendors

WizRecently, we introduced the Wiz AI Application Protection Platform (AI-APP) to secure AI-native applications end-to-end and provide the context needed to understand real risks across models, agents, data, and

Products

Green AgentWiz automates this path to remediation using the Green Agent, solving AI risks at AI speed. Because the Green Agent understands exactly where the exploitable vulnerability stems from in the codebase, it generates aRed AgentA key component of our approach to AI involves Red Agent, our AI-powered attacker that actively probes endpoints the way a threat actor would. For example, a SQL injection detected in code is mapped to the virtualWiz AI Application Protection Platform (AI-APP)Recently, we introduced the Wiz AI Application Protection Platform (AI-APP) to secure AI-native applications end-to-end and provide the context needed to understand real risks across models, agents, data, andWiz Codecode, validating exploitability at runtime, and remediating with agents that understand your codebase, Wiz Code serves as the security fabric for AI-native development, securing the entire lifecycle from prompt toWiz SASTexact same AI risks detected in running cloud workloads are also identified during early development via Wiz SAST. To standardize this continuous detection, our rules engine leverages emerging industry benchmarks,

Related Articles