GuardFall Bypass Exploits Shell Injection in Open-Source AI Coding Agents
New research from Adversa AI, dubbed 'GuardFall,' reveals that ten out of eleven popular open-source AI coding agents are vulnerable to a…
New research from Adversa AI, dubbed 'GuardFall,' reveals that ten out of eleven popular open-source AI coding agents are vulnerable to a…
Adversa AI, a cybersecurity research firm, identified the GuardFall bypass affecting ten open-source AI coding agents, exploiting shell injection techniques to execute…
The Continue AI coding agent was the only one among eleven tested that defended against GuardFall by parsing commands as Bash would,…
Adversa AI demonstrated a full end-to-end attack against the production Plandex binary, exploiting the GuardFall bypass to execute malicious shell commands.
The Hermes project was where the GuardFall vulnerability first surfaced, documented in its issue tracker, affecting its AI coding agent.