OpenClaw Copilot CLI Wrapper

Run GitHub Copilot CLI via exec to generate code, edit files, or automate shell tasks using advanced AI models like Claude or GPT-5.

This skill is coherent with its stated purpose (wrapping the GitHub Copilot CLI) but it instructs you to run Copilot with flags and modes that can access and transmit local files and session data. Before installing/use: 1) Only install the copilot binary from official sources (npm/@github or Homebrew). 2) Avoid using --allow-all / --yolo unless you understand and accept that Copilot may access local files, URLs, and system tools. 3) Be cautious about AGENTS.md auto-loading and session outputs (session.md, ~/.copilot/logs) — these can contain workspace content; review them and store them securely. 4) Consider running Copilot in a sandbox/container or a copy of the workspace with sensitive data removed. 5) If you enable autonomous agent invocation, restrict when and how this skill can be called (or require explicit user confirmation) because the combination of autonomous calls + broad flags increases exposure risk. If you want, I can suggest safer invocation flags and a minimal test workflow to verify behavior in a controlled environment.

Type: OpenClaw Skill Name: openclaw-copilot-cli Version: 1.0.0 The SKILL.md explicitly instructs the OpenClaw agent to execute the `copilot` CLI with the highly permissive `--allow-all` (or `--yolo`) flag. This flag grants the `copilot` CLI, and by extension the agent, broad capabilities including arbitrary file system access, network requests, and shell command execution. This creates a significant remote code execution (RCE) and data exfiltration risk, as a malicious prompt could exploit these permissions to compromise the host system. While not directly malicious code, this configuration introduces a severe vulnerability.