Oc

Comprehensive diagnostic, error-fixing, and skill recommendation tool for OpenClaw

This package appears to be what it claims: a local OpenClaw diagnostic and auto-fix suite. Before installing/using it: 1) Review the scripts (especially self-updater.py and any code that performs network requests) for where they fetch updates or send data. 2) Run it in a non-production sandbox or with dry-run options first (many commands have --dry-run or --check modes). 3) Back up openclaw.json and any configs before applying auto-fixes (the tool documents backups but verify behavior). 4) Be cautious granting sudo/root or allowing destructive fixes (kill -9, systemctl start, global npm installs, downloads to /opt). 5) If you need to trust network endpoints, confirm the project's GitHub/homepage and consider auditing clawhub_client/doc_fetcher calls to ensure no secret exfiltration. If you want higher assurance, request a code audit or run the scripts in a readonly / isolated environment first.

Type: OpenClaw Skill Name: openclaw-doctor-pro Version: 1.1.0 This skill bundle is classified as suspicious due to its extensive use of high-risk capabilities, including the execution of arbitrary shell commands (e.g., `kill -9`, `systemctl start docker`, `npm install -g`) and direct file system modifications (create, delete, change permissions) via `scripts/lib/fix_step_executor.py` and `scripts/lib/utils.py`. While these actions are presented as necessary for diagnostic, error-fixing, and setup purposes, and many impactful 'fix recipes' in `data/fix-recipes.json` are marked as requiring user confirmation (`safe_auto: false`), the broad permissions to execute system commands and alter configurations without clear malicious intent still pose a significant risk. No explicit prompt injection attempts or data exfiltration to unauthorized endpoints were detected.