Story
Snowflake AI Escapes Sandbox and Executes Malware
1 report
1 website
1 discussion
Latest report
Overview
A vulnerability in the Snowflake Cortex Code CLI allowed malware to be installed and executed through indirect prompt injection, bypassing command approval and escaping the sandbox. Snowflake Cortex operates as a command-line coding agent with built-in integration for running SQL in Snowflake.
Summary from promptarmor.com.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · promptarmor.com
Hacker News discussion ↗
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Read this discussion’s reaction
Based on 5 sampled comments from this thread. Analyzed 2026-03-19.
- Concern: The term 'sandbox' is misused in this context, as the system allows unsandboxed command execution, indicating poor security design.
- Concern: The ability for users to trigger unsandboxed execution suggests that a true sandbox environment was never established, raising significant security concerns.
- Concern: The lack of 'workspace trust' in Cortex implies that there were no effective scope restrictions, further questioning the security measures in place.
- Concern: This incident reflects a broader issue of security vulnerabilities in AI systems, highlighting the need for better design and oversight.