敏感信息检测与可逆脱敏工具：在 Agent 对话链路里做强制隐私保护
介绍 SkillHub 社区 Skill「敏感信息检测与可逆脱敏工具」（@user_cf24022c/sensitive-detector v2.0.1）：对手机号、身份证、银行卡等文本做可逆脱敏，本地 OCR 检测图片并拒绝处理，拦截绕过意图，支持最长一天的临时禁用。无需 API Key。文章说明定位、四项核心能力、基于 skillhub CLI 的安装路径（含 Cursor 等目录），以及适用场景与使用注意，并附官方页面与安装文档链接。
Read MoretwoFactor Skill: Implementing TOTP/OTP Two-Factor Authentication in Better Auth
twoFactor is the official Better Auth Agent Skill that explains how to configure the twoFactor plugin and twoFactorClient in an application, covering the complete 2FA lifecycle, including TOTP authenticators, email/SMS OTP, backup codes, the twoFactorRedirect login flow, trusted devices, and encrypted storage. Based on the official SKILL documentation, this article compiles installation commands, migration steps, and typical code examples. It is suitable for developers who need MFA and already use Better Auth, enabling coding assistants to generate configurations according to official practices rather than fragile single-factor approaches.
Read Moredsh-vulnerability-remediation-proof: Offline Evidence Plugin for Patch Verification
`dsh-vulnerability-remediation-proof` is a plugin in the DSH ecosystem that provides an offline, deterministic method for patch verification. It does not perform scanning or installation; instead, it recomputes settlement verdicts from receipts using hashes and restricted metadata to prove a closed remediation loop. The tool is compatible with DeepSeek Harness 0.1.2-alpha.4 and Node.js 22. It uses the `verify` command to validate the provided evidence file and ensure that the patch meets zero-residual closure conditions, making it suitable for scenarios requiring strict audit and security compliance.
Read Moredsh-runtime-nutrition-label: DeepSeek Harness Runtime Nutrition Label Plugin
`dsh-runtime-nutrition-label` is a community-maintained plugin for DeepSeek Harness designed to address information asymmetry between a plugin’s declared capabilities and its actual runtime behavior. It generates JSON snapshots that include declarations, observations, and inferred evidence by using observation tools and filesystem events. The plugin supports network scanning, metric collection, and automatic integration, and follows a privacy-first model (it does not log credentials or sensitive content). Developers can retrieve snapshots via the `/nutrition-label` command or an API for local diagnostics and compliance verification.
Read MoreDSH Telemetry Redactor: Credential Redaction for Exported Telemetry Copies
`dsh-telemetry-redactor` is a community-maintained MIT-licensed plugin designed to reduce the risk of sensitive data leakage when session telemetry is transmitted externally in DeepSeek Harness (DSH). This plugin is mounted on the official telemetry waterfall, applying recursive redaction only to the outbound copies sent to the backend, while leaving the original canonical session log unchanged and without altering existing telemetry backend configurations. Its redaction scope covers three categories of content: values under high-risk key names (such as token, password), Bearer/Basic authentication information embedded in strings, and common credential patterns (such as s
Read More