Task Supervisor

Manage complex tasks with 5+ steps or duration >20 min, tracking progress via task files and sending periodic status reports until completion or pause.

Do not enable this skill yet. Ask the publisher to clarify: (1) which messaging platform will be used (WhatsApp or Feishu?) and exactly how recipient identity and authentication are provided (what env vars or agent integrations are required); (2) whether the agent runtime actually provides an 'openclaw' CLI and what privileges that CLI has; (3) where .tasks/ will be stored and who can read those files; and (4) how and when the cron jobs are removed and what safeguards exist to prevent repeated unintended messages. If you proceed, require explicit, per-task consent before creating background crons or sending messages, and ensure messaging credentials are scoped and stored securely (not left implicit).

Type: OpenClaw Skill Name: task-supervisor Version: 1.0.0 The skill is classified as suspicious due to its use of high-risk capabilities that, while seemingly intended for legitimate task management, create significant vulnerabilities. Specifically, the `SKILL.md` instructs the agent to use `exec` to create cron jobs, which is a powerful primitive allowing arbitrary command execution and establishing persistence. Furthermore, the `--message` argument for the `openclaw cron add` command acts as a prompt for a sub-agent, instructing it to read a file (`.tasks/<SLUG>.md`) and send its content via Feishu. This nested prompt injection surface, combined with file read and exfiltration capabilities, presents a critical vulnerability for data exfiltration if an attacker could manipulate the `TASK-SLUG` or inject into the cron message.