Ghostcommit attack hides malicious AI instructions in images


Ghostcommit is a proof of concept that shows how AI assistants used to review software code can be tricked by hidden instructions embedded in images.

The academic ASSET Research Group showed that an attacker can place instructions inside an image file, point to it in an AGENTS.md file, and get an AI coding agent to follow those instructions during a later task.

A pull request is basically a formal “please review and add my changes” request that a developer sends before changes are added to the main version of a software project. Human reviewers and, increasingly, AI coding tools may review the changes before they’re accepted.

Read more…
Source:  MalwareBytes Labs


Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox


Related:

  • Critical RCE Vulnerability Found in Cisco WebEx Extensions, Again — Patch Now!

    July 17, 2017

    A highly critical vulnerability has been discovered in the Cisco Systems’ WebEx browser extension for Chrome and Firefox, for the second time in this year, which could allow attackers to remotely execute malicious code on a victim’s computer. Cisco WebEx is a popular communication tool for online events, including meetings, webinars and video conferences that help ...

  • NSA Advocates Data Sharing Framework

    June 23, 2017

    The economics of cybersecurity are skewed in favor of attackers, who invest once and can launch thousands of attacks with a piece of malware or exploit kit. That’s why Neal Ziring, technical director for the NSA’s Capabilities Directorate, wants to flip the financial equation on bad guys. “We need to conduct defenses in a way that ...