Threat · curated 30 Jun 2026
GuardFall: a universal shell injection vulnerability in open-source AI agents
First reported · updated · 2 reports adversa.ai
Coverage timeline
Why it matters
AI coding agents run shell commands with full user authority, so a universal filter bypass lets attackers execute arbitrary dangerous commands across widely-used open-source agents.
Adversa AI research describes GuardFall, a bypass of AI coding agents' safety filters using decades-old shell injection tricks to execute dangerous commands. The bypass reportedly worked against 10 of 11 tested popular open-source coding and computer-use agents, with only 'Continue' being resistant.