Model Switchboard

Safely configure OpenClaw AI models by validating roles, autoloading backups, blocking unsafe changes, and managing via CLI or Canvas UI.

This skill appears coherent and appropriate for managing OpenClaw models: it only needs access to your OpenClaw config and any provider API keys you already use, and it implements validation, backups and a UI. However, the included security audit flagged two HIGH issues (XSS in the UI and a shell-injection vector in the import flow). The changelog states those issues were fixed, but some files in the submission were truncated so I could not fully verify every fix. Before installing or enabling this skill in production: 1) Inspect switchboard.sh (import_config) to ensure file paths are passed via environment variables (no unescaped shell interpolation). 2) Open ui/index.html and confirm user/model strings are rendered using textContent/createElement (no innerHTML with unescaped values or inline onclick string interpolation). 3) Run the tool in a non-production environment, exercise import/export and UI flows, and confirm backups and rollback work as advertised. 4) If you must trust it in production, run a local security test (attempt model names with special characters, simulate concurrent operations) and ensure backup directory permissions and lockfiles are present. If you want, I can (a) search the provided switchboard.sh and ui files for the exact patterns and report lines that still look risky, or (b) provide a short checklist of commands/tests to run to validate the fixes on your machine.

Type: OpenClaw Skill Name: model-switchboard Version: 3.0.0 The Model Switchboard skill is classified as benign. While a self-audit (`AUDIT-OPUS.md`) revealed several high-severity vulnerabilities (XSS in `ui/index.html`, shell injection in `scripts/switchboard.sh`) and medium-severity issues, the `CHANGELOG.md` and a thorough code review confirm that all these findings have been addressed and fixed in the provided v3.0 files. The skill's core purpose is safe AI model configuration, employing robust safety measures such as fail-closed validation, atomic writes with automatic rollback, and comprehensive input sanitization, demonstrating a strong commitment to security in its design and implementation.