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:
- Apple patches zero-day flaw that could let attackers take control of devices
February 12, 2026
Apple has released security updates for iPhones, iPads, Macs, Apple Watches, Apple TVs, and Safari, fixing, in particular, a zero-day flaw that is actively exploited in targeted attacks. Exploiting this zero-day flaw would allow cybercriminals to run any code they want on the affected device, potentially installing spyware or backdoors without the owner noticing. Installing these ...
- ISA warns of increasing cyber attacks against Israeli officials
February 11, 2026
The ISA and the National Cyber Directorate announced on Wednesday that they thwarted hundreds of cyberattack attempts over the past year carried out by Iranian intelligence operatives. According to the agencies, the attacks targeted senior government and defense officials, academics, journalists, and employees in the defense industry. A joint statement said a marked escalation in hostile ...
- RenEngine: When “free” comes at too high a price
February 11, 2026
Kaspersky researchers often describe cases of malware distribution under the guise of game cheats and pirated software. Sometimes such methods are used to spread complex malware that employs advanced techniques and sophisticated infection chains. In February 2026, researchers from Howler Cell announced the discovery of a mass campaign distributing pirated games infected with a previously unknown ...
- Patch Tuesday – February 2026
February 11, 2026
Microsoft is publishing 55 vulnerabilities this February 2026 Patch Tuesday. Microsoft is aware of exploitation in the wild for six of today’s vulnerabilities, and notes public disclosure for three of those. Earlier in the month, All three of the publicly disclosed zero-day vulnerabilities published today are security feature bypasses, and Microsoft acknowledges the same cast of ...
- Spam and phishing in 2025
February 11, 2026
In 2025, online streaming services remained a primary theme for phishing sites within the entertainment sector, typically by offering early access to major premieres ahead of their official release dates. Alongside these, there was a notable increase in phishing pages mimicking ticket aggregation platforms for live events. Cybercriminals lured users with offers of free tickets to ...
- Beyond the Battlefield: Threats to the Defense Industrial Base
February 10, 2026
In modern warfare, the front lines are no longer confined to the battlefield; they extend directly into the servers and supply chains of the industry that safeguards the nation. Today, the defense sector faces a relentless barrage of cyber operations conducted by state-sponsored actors and criminal groups alike. In recent years, Google Threat Intelligence Group (GTIG) ...
