Self-Prompt

Force agents to respond to automated messages by using `openclaw agent` instead of `openclaw message send`, ensuring tasks from scripts get agent replies.

This skill appears to do exactly what it says: it wraps the openclaw CLI to force an agent response and deliver it to chat. Before installing or running it: 1) Verify the OPENCLAW_PATH used points to your openclaw binary (or set OPENCLAW_PATH explicitly) — the bundled default is an author-specific path. 2) Review and, if desired, change the log path (~/agent_task.log) to a location with appropriate permissions to avoid exposing sensitive output. 3) Avoid including secrets or sensitive data in automated messages sent to agents (they will appear in agent logs and chat). 4) Test in a non-production environment so you can confirm session-key formatting and timeout behavior. Overall the package is coherent, but exercise normal caution when letting automated scripts trigger agent actions.

Type: OpenClaw Skill Name: self-prompt Version: 1.1.0 The skill bundle provides utility scripts and documentation to force OpenClaw agents to respond to automated messages. The `SKILL.md` contains no prompt injection attempts or malicious instructions. Both `send_agent_task.sh` and `send_agent_task.py` scripts correctly use the `openclaw` CLI tool to interact with the platform, without introducing shell injection vulnerabilities (Python uses `subprocess.run` with a list, Bash uses double quotes for arguments). Local logging to `~/agent_task.log` is present but does not constitute data exfiltration. There is no evidence of intentional harmful behavior such as data exfiltration, malicious execution, persistence, or obfuscation.