An AI agent designed to hunt for vulnerabilities independently discovered a flaw within a public Snowflake repository and used it to gain access to the company's internal Jira system. The vulnerability had existed for just five days when discovered, and notably, GitHub Copilot had reviewed the code during that window without flagging the dangerous section. Wiz's Red Agent Uncovers the Flaw…

GuardFall affects 10 of 11 open-source AI agents, letting attackers bypass command filters through a shell injection weakness.

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