tg buttons

Automatically colors Telegram bot choice buttons as default, destructive (red), or secondary (gray) based on the action's criticality and reversibility.

This skill appears to do what it claims (auto-classify and color Telegram choice buttons), but the registry metadata incorrectly lists no required environment variables while the code expects a BOT_TOKEN (and optionally CHAT_ID). Before installing or running: 1) treat your BOT_TOKEN like a secret — don't paste it into public places; 2) inspect the scripts locally (they only scaffold files and call the Telegram API) and run them in a safe environment; 3) confirm that your Telegram Bot token has only the permissions you intend; 4) ask the publisher to correct the metadata to declare BOT_TOKEN/CHAT_ID so the requirements are transparent. If the metadata is fixed, this would likely be benign; the current mismatch is the reason for a "suspicious" rating.

Type: OpenClaw Skill Name: telegram-colored-choices-buttons Version: 1.0.0 This skill bundle is designed to automatically color Telegram choice buttons based on their criticality. All files, including the `SKILL.md` instructions for the AI agent, the Python code snippets, and the shell scripts, are aligned with this stated purpose. The Python code uses standard libraries (`re`, `requests`) to interact with the legitimate Telegram Bot API. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection intended to subvert the agent's core functions. The use of regex for classification is a core feature and does not present a clear malicious intent, nor does it pose a significant vulnerability beyond theoretical ReDoS, which is not indicative of malice.