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:
- Microsoft working on a fix for RoguePlanet, a flaw that grants full PC control
June 18, 2026
A publicly available exploit called RoguePlanet can give attackers the highest level of access on Windows systems. Microsoft has confirmed the vulnerability and says it’s working on a security update. RoguePlanet is tracked under CVE-2026-50656, where it’s described as a Microsoft Defender Elevation of Privilege (EoP) vulnerability. Read more… Source: MalwareBytes Labs Sign up for the Cyber Security Review Newsletter The latest cyber ...
- Kodak confirms breach as ShinyHunters’ leak threat reaches deadline
June 18, 2026
The Eastman Kodak Company (Kodak) confirmed to BleepingComputer that it is investigating a security breach after the ShinyHunters extortion group claimed responsibility for the incident. Kodak is the latest organization to land on the group’s leak site. ShinyHunters claims it stole more than 2.2 million records and threatened to publish the data unless the company responded by June ...
- Cyber Criminals Redirecting Users to Fraudulent Websites with Malicious Traffic Distribution Systems
June 18, 2026
The Federal Bureau of Investigation (FBI) is publishing this Public Service Announcement (PSA) to warn the public of cyber criminal use of traffic distribution systems (TDSs) to gain access to victim networks for ransomware or other financial scams. TDS is a technology used to route internet traffic visitors to different destinations after users visit webpages, click advertisement ...
- Cybercriminals allegedly hacked tens of thousands of Fortinet firewalls used by major companies all over the world
June 17, 2026
Cybercriminals have compromised tens of thousands of Fortinet firewalls and VPNs used by major companies all over the world, according to two cybersecurity firms. The widespread hacking campaign, which is ongoing and has been dubbed FortiBleed, appears to not involve abusing any unknown vulnerability in the targeted devices, but rather on a more basic issue: Companies ...
- Cisco SD-WAN make-me-root bug under attack
June 16, 2026
Cisco today issued a fix for a Catalyst SD-WAN Manager bug that attackers have already spotted and exploited to get root privileges, according to both the networking vendor and the feds. The vulnerability, tracked as CVE-2026-20262, is in the web UI of Cisco Catalyst SD-WAN Manager, and exists because the software is not properly validating user-supplied input during ...
- Hijacking Vertex AI Model Uploads for Cross-Tenant RCE
June 16, 2026
Palo Alto Unit42 discovered a vulnerability in the Google Cloud Vertex AI software development kit (SDK) for Python, and responsibly disclosed it to Google. Before Google’s fix, the vulnerability would have allowed an attacker operating entirely from their own Google Cloud project to hijack a victim’s model upload and poison it. By exploiting this flaw ...