OC Team Builder

Discover, compose, and activate specialist teams from 3 rosters — OpenClaw Core (CEO/Artist), Agency Division (55+ specialists), and Research Lab (autonomous...

This skill appears to do what it says, but it contains scripts that will modify local git repositories, commit/revert code, run arbitrary experiment commands, and write logs (including an explicit 'NEVER STOP' autonomous research loop in the documentation). Before using: 1) Review the scripts (especially experiment.sh and its default run-cmd) and understand the default commands (uv run train.py / grep metric). 2) Run experiments only in isolated test projects or clones (not in production repos or with sensitive data). 3) Ensure you have appropriate resource/time budgets — experiments can be CPU/GPU and time intensive and the script may timeout/kill runs but also can be configured to run repeatedly. 4) Back up or work on disposable branches before allowing commits; expect the script to create branches and commit changes. 5) If you do not want code modified autonomously, do not run the experiment --run flow or remove/lock write/commit permissions. 6) Confirm no sensitive secrets or credentials exist in the project directories the scripts will touch. If you want greater assurance, request the missing scripts that were truncated (plan.sh, review.sh, roster.sh) and a full audit of any default run commands and their downstream effects.

Type: OpenClaw Skill Name: oc-team-builder Version: 2.0.0 The skill bundle implements a multi-agent orchestration system with a 'Research Lab' feature that uses autonomous experiment loops. A significant security concern exists in `scripts/experiment.sh`, which utilizes `eval` to execute strings provided via the `--run-cmd` and `--metric-cmd` arguments, creating a high risk for shell injection. Additionally, the 'autoresearch' methodology described in `references/TEAM-RESEARCH.md` and `SKILL.md` explicitly instructs the AI agent to autonomously modify and execute code (`train.py`) in a continuous loop; while this aligns with the stated purpose of the skill, the combination of `eval` and autonomous execution without strict sandboxing or input validation poses a substantial risk of remote code execution (RCE).