Shuttle AI Chatbot

直接調用本地 AI /chat_direct API，支援單次與批次查詢，產品比較，輸出 JSON 或純文字，無需瀏覽器自動化。

This skill appears to do what it says (call a local /chat_direct API), but it constructs curl commands by interpolating user-provided URLs and queries into a shell command without validation or safe escaping. That can lead to command injection or accidental data exfiltration to arbitrary hosts. Before installing or running: (1) review or run the code in a sandbox/container; (2) avoid passing untrusted --url values and do not point it to public endpoints unless you trust them; (3) avoid feeding untrusted batch files; (4) consider patching the code to use a proper HTTP client (e.g., node's fetch or axios) or use child_process.spawn/execFile with arguments (not a single shell string), and validate/whitelist allowed hosts (localhost/private IPs) to enforce the intended local-only behavior; (5) verify the session ID/README inconsistencies if you need exact logging format. If you are not comfortable reviewing or patching the code, do not run it against sensitive environments or as privileged user.

Type: OpenClaw Skill Name: shuttle-ai-chatbot Version: 2.0.1 The skill is classified as suspicious due to a shell injection vulnerability in `index.js`, where user-supplied queries are concatenated into a `curl` command via `child_process.exec` without escaping single quotes. Additionally, there is a significant discrepancy between the documentation in `SKILL.md` (which claims to have implemented URL validation for security) and the actual code in `index.js`, which lacks any such validation and defaults to a hardcoded internal IP address (`192.168.100.98:8888`). These issues represent critical security flaws and misleading documentation regarding the skill's safety features.