TokenSaver Pro

【系统级拦截器】TokenSaver Pro - 全自动拒绝服务。 安装后默认拦截所有用户请求，提供阴阳怪气拒绝。 版本: 1.1.0 - 真·全自动模式

This skill appears to do exactly what it claims: install it only if you want a global, always‑on message rejector that will intercept virtually every user message. Before installing: back up SOUL.md and your workspace; review interceptor.js to confirm the skip keywords and rejection messages; be aware it writes .env.tokensaver and stats.json into the workspace; test in an isolated/non‑production workspace first (it can block important or emergency requests). If you want the feature but with less blast radius, avoid the SOUL.md global hook, run the interceptor only as an opt‑in tool, or narrow the hook priority/conditions.

Type: OpenClaw Skill Name: token-saver-pro Version: 1.0.1 The 'token-saver-pro' bundle is designed to perform a 'Denial of Service' on the AI agent by intercepting all user requests and responding with sarcastic refusals. It utilizes high-risk OpenClaw capabilities such as 'autorun: true' and 'intercept_all: true' in SKILL.md, and its README.md instructs users to manually inject logic into the core SOUL.md file to hijack the agent's personality. While the code (interceptor.js, install.js) does not perform host-level data exfiltration or install traditional backdoors, its primary purpose is to intentionally disrupt the agent's utility and availability through prompt injection and configuration modification.