OpenClaw CLAUDE BRIDGE

Use when user asks about Bridge to local Claude Code CLI - no API key required

This skill is plausible for running a local Claude CLI, but there are clear mismatches and risky behaviors you should weigh before installing: - Inconsistency: metadata claims no binaries/configs required, but SKILL.md and code require the 'claude' CLI and expect access to your ~/.openclaw/workspace and other skill directories. - Broad filesystem actions: many task scripts (tasks/*.sh) and generated scripts ask Claude to read and edit files across the workspace (other skills and core files). The Python wrapper creates and executes shell scripts via subprocess.run. - Effective privileges: although the skill isn't declared 'always' enabled, when invoked it can create/execute scripts that perform wide-ranging edits. That can modify other skills or code in your workspace. Recommendations before using: 1. Inspect the code yourself (claude_bridge.py and tasks/*.sh/.json) and the generated scripts to confirm exactly what will run. 2. Do not run it on a production or sensitive workspace. Try it in an isolated/sandbox environment or throwaway VM/container with a fake ~/.openclaw workspace. 3. If you proceed, ensure file permissions limit its write access, and review all generated task scripts before executing them. 4. Consider whether you want a skill that can instruct the model to use Read/Edit/Bash on arbitrary files — if not, avoid installing. If you want, I can point out the exact lines that create/execute shell scripts and the tasks that ask for full filesystem edits so you can review them more quickly.

Type: OpenClaw Skill Name: openclaw-claude-bridge Version: 1.0.0 The 'claude-bridge' skill acts as a wrapper for the Claude Code CLI, providing a mechanism to generate and automatically execute shell scripts containing AI-generated commands. The core logic in `claude_bridge.py` uses `subprocess.run` to execute bash scripts that grant the AI full 'Read, Edit, Bash' permissions over the local filesystem. While the included tasks in the `tasks/` directory (e.g., `fix_db_cache_002.sh`, `fix_web_ui_full_access.sh`) appear to be for legitimate development purposes like refactoring and analysis, the architecture creates a high-risk environment for Remote Code Execution (RCE) without adequate sandboxing or input sanitization. The tool also includes scripts to deeply analyze the host's OpenClaw architecture and source code, which could be used for reconnaissance.