HackerFeeds

CyberSecurity News

New Gaslight macOS Malware Uses Prompt Injection to Disrupt AI-Assisted Analysis

The Hacker News
· June 25, 2026

AI summary

A newly discovered macOS malware, codenamed Gaslight, has been found to use a prompt injection payload to disrupt analysis by AI-assisted tools. This Rust-based implant and information stealer is designed to trick AI tools into aborting or refusing to analyze it. The malware's deceptive behavior is the reason for its codename, Gaslight. It is believed with high confidence that the tool has a specific purpose, although its exact nature is not specified. The malware's ability to evade analysis makes it a notable threat. Its discovery highlights the growing complexity of malware tactics.

Read the full article at The Hacker Newsthehackernews.com/2026/06/new-gaslight-macos-malware-uses-prompt.html

This is an AI-generated brief aggregated by HackerFeeds for convenience and grounded in the source’s own summary; the related CVE, threat-group and country data is from HackerFeeds’ own indexes. The original article is the authoritative source — all rights belong to The Hacker News.