Security Vulnerability in Snowflake Cortex Code CLI Allows Malware Execution via Prompt Injection
By
ozgune
If you only eat one bagel today, this is the bagel.
Summary
A security vulnerability was discovered in Snowflake's Cortex Code CLI tool just two days after its release. The vulnerability allowed attackers to bypass the tool's command validation system through indirect prompt injection, enabling malicious commands to download and execute scripts without human approval. This could lead to data exfiltration and other malicious actions using the victim's active credentials within Snowflake's environment.
Key quotes
· 3 pulledTwo days after release, a vulnerability was identified in Cortex Code's command validation system that allowed specially constructed malicious commands
via indirect prompt injection, an attacker could manipulate Cortex to download and execute scripts without approval that leverage the victim's active credentials to perform malicious actions in Snowflake
A vulnerability in the Snowflake Cortex Code CLI allowed malware to be installed and executed via indirect prompt injection, bypassing human-in-the-loop command approval and escaping the sandbox
You might also wanna read
VS Code Remote-SSH Vulnerability Enables Lateral Movement from Developer Machines to Cloud Servers
A critical vulnerability in Visual Studio Code's Remote-SSH extension creates a post-compromise attack path enabling threat actors to pivot
cybersecuritynews.com·3d ago
Microsoft uncovers supply chain attack: Compromised @antv npm packages steal CI/CD credentials via Mini Shai-Hulud malware
Microsoft has identified an active supply chain attack targeting the @antv npm package ecosystem. A threat actor compromised an @antv mainta
Hacker Exploits AI Coding Agent Vulnerability to Install OpenClaw Malware
A hacker exploited a vulnerability in Cline, an open-source AI coding agent, to trick it into installing OpenClaw (a viral AI agent) on comp
The Verge·3mo ago
Prompt Injection Attacks: The Top Security Threat Hijacking AI Chatbots
Prompt injection attacks are a critical security vulnerability in AI systems where hidden instructions within user data (like emails or docu
buff.ly·15h ago