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:
- High-Severity Cisco DoS Flaw Can Immobilize ASR Routers
November 11, 2020
A high-severity flaw in Cisco’s IOS XR software could allow unauthenticated, remote attackers to cripple Cisco Aggregation Services Routers (ASR). The flaw stems from Cisco IOS XR, a train of Cisco Systems’ widely deployed Internetworking Operating System (IOS). The OS powers the Cisco ASR 9000 series, which are fully distributed routers engineered to address massive surges ...
- Recent ransomware wave targeting Israel linked to Iranian threat actors
November 11, 2020
Two recent ransomware waves that targeted Israeli companies have been traced back to Iranian threat actors, multiple sources have told ZDNet today. The ransomware attacks have been taking place since mid-October, have ramped up this month, and have repeatedly focused on Israeli targets. Israeli companies of all sizes have been targeted by threat actors using the Pay2Key ...
- CVE-2020-17051: Remote kernel heap overflow in NFSv3 Windows Server
November 10, 2020
Microsoft released a patch today for a critical vulnerability (CVE-2020-17051) in the Windows NFSv3 (Network File System) server. NFS is typically used in heterogenous environments of Windows and Unix/Linux for file sharing. The vulnerability can be reproduced to cause an immediate BSOD (Blue Screen of Death) within the nfssvr.sys driver. Interestingly, the November patches from ...
- New Platypus attack can steal data from Intel CPUs
November 10, 2020
A team of academics has disclosed today a new attack method that can extract data from Intel CPUs. Named Platypus, an acronym for “Power Leakage Attacks: Targeting Your Protected User Secrets,” the attack targets the RAPL interface of Intel processors. RAPL, which stands for Running Average Power Limit, is a component that allows firmware or software applications ...
- A Closer Look at the Web Skimmer
November 9, 2020
The formjacking attack has been one of the fastest-growing cyberattacks in recent years. As explained in our previous blog, “Anatomy of Formjacking Attacks,” the formjacking attack is easy to deploy but hard to detect. It has gained popularity among threat actors, especially against e-commerce websites. Between May and September 2020, we detected an average of ...
- Ghimob: a Tétrade threat actor moves to infect mobile devices
November 9, 2020
Guildma, a threat actor that is part of the Tétrade family of banking trojans, has been working on bringing in new techniques, creating new malware and targeting new victims. Recently, their new creation, the Ghimob banking trojan, has been a move toward infecting mobile devices, targeting financial apps from banks, fintechs, exchanges and cryptocurrencies in ...