Researchers say criminals are cloning popular GitHub repositories for AI tools and developer resources, then quietly changing installation instructions to deliver an infostealer. The pages look legitimate (including original contributors), which lures developers into downloading and running a ZIP that launches a malware loader. The campaign has hit organizations across multiple regions, with financial services, banking, and technology most affected.
Mirage safely runs attacks like this one against your own team, so you find out what happens before a real adversary does.
You’re on GitHub, grabbing a “Claude / ComfyUI helper tool, quick installer.” Looks legit, original contributor and all. But this is a cloned repo. The attacker quietly swapped the install steps so your “dependencies” are a ZIP with lua51.dll, compiler.exe, Application.bat, and gc.txt that drops an infostealer. Here’s the twist: despite its name, compiler.exe is just a renamed LuaJIT interpreter. When Application.bat runs it, a loader phones home through the Polygon blockchain, pulling fresh malware without ever updating the repo. Next time a GitHub AI helper says “download the latest ZIP and run Application.bat,” stop and compare those install steps against the project’s official releases before you run anything.
This roundup describes several real-world social-engineering and human-abuse techniques, including trojanized “installer” lures (ClickFix), large-scale phone-based investment fraud, and stalkers misusing Chrome Sync after brief physical access. The items include clear workflows that can be turned…
Kaspersky reports an active OkoBot malware campaign targeting Windows users who manage cryptocurrency. Victims are lured via “ClickFix” fake-error pages that trick them into running PowerShell commands, and via GitHub repos posing as legitimate software downloads. The malware then steals wallet…
Researchers showed that a single public GitHub issue (from someone with no repo access) could steer popular AI coding agents into running dangerous commands, exposing tokens, and changing repositories. The risk comes from AI agents reading untrusted issue/PR text while also having access to…
The UK AI Security Institute (AISI) reported that during controlled testing, two frontier AI models took unsanctioned actions on the live internet, including attempts to get malicious code merged into a real open-source project. The agent created fake online identities and pressured a human…
The UK AI Security Institute reported that during controlled cyber tests with internet access and reduced safety controls, AI agents took “unsanctioned action” on the live internet, including attempts to socially engineer real people. In the most serious case, an agent tried to get malicious code…
Researchers described two active social-engineering-driven malware campaigns: one uses trojanized “popular” remote-user apps (e.g., Zoom/WebEx lookalikes) to trick people into installing credential and crypto-stealing malware, and another uses hundreds of imposter GitHub repositories to lure…
