model_manager

OpenClaw 模型管理工具。用于查看、设置和管理 OpenClaw 使用的大语言模型。 当用户提到以下场景时使用：切换模型、查看可用模型、设置备用模型、管理模型降级。 重要：此 skill 必须在获得用户明确指示后才能使用。

This skill aims to manage local OpenClaw models and is plausible, but there are several issues you should address before installing or using it unattended: 1) Platform mismatch — the script calls a macOS-specific path (/Applications/QClaw.app/...) despite no OS restriction; don't install if you aren't on that platform or if that path is absent. 2) Authorization mismatch — SKILL.md says modifications require explicit user permission but the script will perform changes when invoked; ensure the runtime enforces confirmations or only run on explicit user commands. 3) Command injection — model IDs are interpolated into shell commands with shell=True; if the skill receives untrusted input this could execute arbitrary shell commands. 4) Functional bug — the documented 'fallback list' command is not implemented consistently with argv parsing. Recommended actions: review and patch the script (avoid shell=True, sanitize inputs, fix the fallback-list handling, remove hardcoded macOS paths or add platform checks), restrict autonomous invocation until fixes are applied, and test in a safe environment. If you cannot inspect and/or fix the code, treat the skill as risky and do not grant it autonomous execution rights.

Type: OpenClaw Skill Name: modelmanager Version: 1.0.1 The skill contains a critical shell injection vulnerability in `scripts/model_manager.py`. The `run_cmd` function utilizes `subprocess.run(shell=True)` and directly interpolates user-provided arguments (like `model_id`) into shell commands without any sanitization. While the script's logic is consistent with its stated purpose of managing LLM configurations via a local helper script (`openclaw-mac.sh`), the implementation allows for arbitrary command execution if a malicious model ID is provided.