In April 2023, Google announced VirusTotal Code Insight to improve the capacity of its malware detection and analysis platform. This week, Google released an enhanced version of VirusTotal Code Insight, including support for more scripting languages.
Code Insight is an AI-based code analysis feature powered by the Google Cloud Security AI Workbench that uses the Sec-PaLM large language model (LLM) tailored for security use cases.
“Code Insight has broadened its support for script formats, moving beyond PowerShell to offer analysis for various scripting languages,” VirusTotal founder Bernardo Quintero said.
Code Insight, which was once limited to analyzing a subset of PowerShell files, can currently detect malicious Batch (BAT), Command Prompt (CMD), Shell (SH), and VBScript (VBS) scripts.
The maximum file size limit for files handled by Code Insight has been doubled, allowing for an analysis of larger files.
Further, the model provides more brief and concentrated high-level explanations, emphasizing code behavior.
The user interface has been modified to display only the initial sentences of the report by default, with the option for users to expand the report as needed, preventing lengthy reports from overpowering the default view.
The functionality is currently in active development and should be regarded as beta. In the upcoming months, VirusTotal intends to enhance it by supporting more file formats, bigger file sizes, and the analysis of executable file types like.exe.
For example, the team intends to provide the study with more context by granting the AI access to “any metadata related to the URLs and files linked in the code snippet.”
Security researchers and other users can utilize Code Insight to analyze the behavior of scripts, making it an intriguing feature. Its use will increase when the service is expanded to support more file types, particularly executable files.
Struggling to Apply The Security Patch in Your System? –
Try All-in-One Patch Manager Plus
Attackers abused compromised ConnectWise Cloud Backup credentials to access Microsoft 365 customer environments, prompting ConnectWise…
Anthropic says an internal Claude research model reconstructed how the National Security Agency generated seeds…
Two WordPress Core vulnerabilities can be chained to execute remote code without authentication, according to…
A newly disclosed OpenBSD kernel exploitation chain combines a shared memory accounting flaw with a…
GhostAction attackers have expanded their GitHub credential theft campaign with a second stage that disguises…
Indian authorities have warned that SideCopy hackers are targeting Indian organizations, including academic institutions, with…