Pocketalert

The Pocket Alert (pocketalert.app) skill for OpenClaw enables OpenClaw agents and workflows to send push notifications to iOS and Android devices. It is used to deliver alerts and updates from automated tasks, workflows, and background processes.

This instruction-only skill appears to be a straightforward wrapper around the Pocket Alert CLI, but proceed cautiously. Before installing or using it: 1) Verify the CLI download URL (info.pocketalert.app) and prefer official releases or checksums; 2) Confirm the Pocket Alert service is legitimate (look for a homepage, privacy/security policy, and upstream source code or documentation) — the registry metadata here lacks a homepage; 3) Avoid pasting your primary API key into tools you don't fully trust; consider creating a scoped API key for automation; 4) Be aware the skill's examples run host commands (uptime, systemctl) and reference ~/.pocketalert/config.json — these can expose secrets or system state if an agent executes them; restrict agent permissions or run on a low-privilege host; 5) If you need higher assurance, ask the publisher for source code or a homepage and prefer an install path via a known release host (GitHub releases, vendor site) rather than an unknown package. If you cannot verify the CLI or publisher, treat this skill as higher risk and avoid giving it real credentials or allowing autonomous execution on sensitive systems.

Type: OpenClaw Skill Name: pocketalert Version: 1.0.2 The skill is classified as suspicious due to several risky capabilities, even though they are presented for legitimate purposes. The `SKILL.md` file instructs the agent to download and execute an external binary from `https://info.pocketalert.app/cli.html`, which is a supply chain risk. Furthermore, it demonstrates the execution of local commands like `uptime`, `hostname`, and `systemctl` to generate message content, indicating the agent's capability to run arbitrary shell commands. Finally, the ability to set a custom `base_url` for the API client could allow redirection of all API traffic to an arbitrary endpoint, posing a potential data exfiltration or redirection risk.