AI/ML

StackHawk launches Wingman to fix AI-generated code vulnerabilities

Visualizing the dangers of unreliable algorithms and model collapse in artificial intelligence.

StackHawk Inc. has launched Wingman, a new tool designed to automatically fix security vulnerabilities within the artificial intelligence coding sessions that produce flawed code. The software integrates into agentic coding workflows, including popular tools like Claude Code, Cursor, and GitHub Copilot, aiming to streamline the security patching process, as reported by Silicon Angle.

Wingman activates when an AI coding agent completes a feature, automatically configuring itself to probe the running application like an attacker would, eliminating the need for manual setup. Identified vulnerabilities are then sent back to the AI agent that generated the code for patching. A subsequent scan verifies the repair before a pull request is opened.

StackHawk argues that the AI agent's inherent understanding of the application's architecture and dependencies makes Wingman more effective than traditional scanners. The tool supports various AI coding agents, including Codex and Antigravity, and provides continuous integration pipelines with a record of security scans for each commit. In early access, Wingman reportedly fixed over 7,000 vulnerabilities, with 98% of repairs proving effective.

Source: Silicon Angle

An In-Depth Guide to AI

Get essential knowledge and practical strategies to use AI to better your security program.

Get daily email updates

SC Media's daily must-read of the most current and pressing daily news

By clicking the Subscribe button below, you agree to SC Media Terms of Use and Privacy Policy.

You can skip this ad in 5 seconds