Project
Qwen Code is Alibaba's open-source command-line AI coding agent, built around Qwen models, that reads, edits and runs code in a developer's local project.
Gemini CLI skips a yolo value in settings.json and never turns on the sandbox for it, a dev.to read of the source found. Anyone who wants YOLO every session needs a shell alias and an explicit --sandbox.
Reality
Sakana AI and UC Berkeley's MASS method reached a 69.9% win rate against its Qwen3.6-27B base model after two rounds of self-training. The same model ranks its own runs, and its evaluator sometimes passes flawed steps into the next training set.
Reality
Manifold Security reported eight instances across seven command-line agents. The command runs as the user, outside the sandbox, with no approval prompt, and four were still firing when the researchers retested on September 1.
Reality
GitSpawn, as summarised in a dev.to write-up of Cloud Security Alliance findings, uses a Git performance setting to run attacker code when a coding agent inspects a project it just opened. Seven agents are named.
Reality
Manifold Security's GitSpawn findings cover eight issues across seven coding agents. The path runs through core.fsmonitor, where a background git status starts a helper the repository chose, outside the agent's sandbox and with no prompt.
Reality
The wiki's old software took a plain GET as an edit, so a harness that policed request types could not stop the writes. GitSpawn puts the same gap in the startup git calls of seven coding agents.
Reality
The spread traces to two numbers you can read off your own logs: the tokens a harness spends before any work starts, and how many turns it takes. Together they predicted total token use with an R-squared of 0.99.
Reality
A frozen Claude Code session moved cleanly into seven rival agent formats. The approval and audit machinery wrapped around it moved into none of them.
Reality