GuardFall Exposes Open-Source AI Coding Agents to Decades-Old Shell Injection Risks

0 Replies 1 Views
·

Leave a rating: GuardFall Exposes Open-Source AI Coding Agents to Decades-Old Shell Injection Risks

You have already rated this thread. Re-rating it will remove your existing rating or review.

Rating:

Raters: GuardFall Exposes Open-Source AI Coding Agents to Decades-Old Shell Injection Risks

Participants
Thread Starter #0
The safety check that is supposed to stop an AI coding agent from running a dangerous command can be walked straight past using a shell trick that has been public for decades. New research from Adversa AI, which is named the bypass GuardFall, found it works against ten of the eleven popular open-source coding and computer-use agents the firm tested. Only one, "Continue," was built to

Okumaya devam et...

You must be logged in to reply.

0 quotes selected