By exploiting how AI coding agents retrieve and verify plugins, researchers were able to execute malicious code even when the agent was told to use a trusted, approved version.
Compare 11 open-source agent harnesses for local LLMs, including OpenCode, Pi, Goose, Cline, OpenHands, Aider, and Codex CLI.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results