Workspace Casual Lucas

Offers a casual interface to list files, run commands, read files, and automate tasks in your OpenClaw workspace.

This skill legitimately implements a workspace helper, but it exposes two powerful actions: running arbitrary shell commands and reading arbitrary files. Before installing, consider: 1) Do you trust the author and host environment? 2) Restrict or remove run_command if you don't need arbitrary shell execution — replace it with a limited set of safe operations. 3) Add input validation and path sandboxing (limit to a single workspace directory). 4) Disable autonomous invocation (set disable-model-invocation = true) or require explicit user confirmation before running commands. 5) Review and, if needed, remove triggers that expose these actions to external channels (triggers.json lists "whatsapp"). 6) Run the skill in an isolated/sandboxed account or container if you must use it. If you cannot apply these mitigations, avoid installing this skill on agents with network access or elevated privileges.

Type: OpenClaw Skill Name: workspace-casual-lucas Version: 1.0.3 This skill is classified as suspicious due to severe vulnerabilities that allow arbitrary shell command execution and arbitrary file reading. The `index.js` file directly uses `child_process.execSync` and `fs.readFileSync` with unsanitized user input for the `run_command` and `open_file` functions, respectively. The `triggers.json` file directly exposes these functions to user input, making them exploitable for Remote Code Execution (RCE) and information disclosure. While there is no explicit code for data exfiltration, persistence, or other malicious intent, these critical vulnerabilities pose a significant security risk.