隐私审计
Privacy
by BytesAgain
Audit and harden privacy settings across systems. Use when generating reports, checking data exposure, rotating encryption keys, auditing access logs.
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/bytesagain3/privacy文档
Privacy
Take control of Privacy with this security toolkit. Clean interface, local storage, zero configuration.
Why Privacy?
- Works entirely offline — your data never leaves your machine
- Simple command-line interface, no GUI needed
- Export to JSON, CSV, or plain text anytime
- Automatic history and activity logging
Getting Started
# See what you can do
privacy help
# Check current status
privacy status
# View your statistics
privacy stats
Commands
| Command | What it does |
|---|---|
privacy generate | Generate |
privacy check-strength | Check Strength |
privacy rotate | Rotate |
privacy audit | Audit |
privacy store | Store |
privacy retrieve | Retrieve |
privacy expire | Expire |
privacy policy | Policy |
privacy report | Report |
privacy hash | Hash |
privacy verify | Verify |
privacy revoke | Revoke |
privacy stats | Summary statistics |
privacy export | <fmt> Export (json |
privacy search | <term> Search entries |
privacy recent | Recent activity |
privacy status | Health check |
privacy help | Show this help |
privacy version | Show version |
privacy $name: | $c entries |
privacy Total: | $total entries |
privacy Data | size: $(du -sh "$DATA_DIR" 2>/dev/null |
privacy Version: | v2.0.0 |
privacy Data | dir: $DATA_DIR |
privacy Entries: | $(cat "$DATA_DIR"/*.log 2>/dev/null |
privacy Disk: | $(du -sh "$DATA_DIR" 2>/dev/null |
privacy Last: | $(tail -1 "$DATA_DIR/history.log" 2>/dev/null |
privacy Status: | OK |
privacy [Privacy] | generate: $input |
privacy Saved. | Total generate entries: $total |
privacy [Privacy] | check-strength: $input |
privacy Saved. | Total check-strength entries: $total |
privacy [Privacy] | rotate: $input |
privacy Saved. | Total rotate entries: $total |
privacy [Privacy] | audit: $input |
privacy Saved. | Total audit entries: $total |
privacy [Privacy] | store: $input |
privacy Saved. | Total store entries: $total |
privacy [Privacy] | retrieve: $input |
privacy Saved. | Total retrieve entries: $total |
privacy [Privacy] | expire: $input |
privacy Saved. | Total expire entries: $total |
privacy [Privacy] | policy: $input |
privacy Saved. | Total policy entries: $total |
privacy [Privacy] | report: $input |
privacy Saved. | Total report entries: $total |
privacy [Privacy] | hash: $input |
privacy Saved. | Total hash entries: $total |
privacy [Privacy] | verify: $input |
privacy Saved. | Total verify entries: $total |
privacy [Privacy] | revoke: $input |
privacy Saved. | Total revoke entries: $total |
Data Storage
All data is stored locally at ~/.local/share/privacy/. Each action is logged with timestamps. Use export to back up your data anytime.
Feedback
Found a bug or have a suggestion? Let us know: https://bytesagain.com/feedback/
Powered by BytesAgain | bytesagain.com | hello@bytesagain.com
相关 Skills
安全专家
by alirezarezvani
覆盖威胁建模、漏洞评估、安全架构设计、代码审计与渗透测试，内置 STRIDE、OWASP、加密模式和安全扫描流程，适合系统设计评审与上线前安全排查。
✎ 安全专家把威胁建模、漏洞分析到渗透测试串成一套流程，内置 STRIDE 与 OWASP 指南，做安全设计和排查更省心。
安全运营
by alirezarezvani
覆盖应用安全、漏洞管理与合规审计，支持代码/依赖扫描、CVE 评估、Secrets 检测和安全自动化，适合做安全基线落地、漏洞响应、审计检查与安全开发治理。
✎ 应用安全、漏洞管理和合规检查一套打通，还能自动化扫描与响应，帮团队更早发现并收敛风险。
安全审计
by alirezarezvani
安装前审计 Claude Code Skill 的代码执行、Prompt 注入和依赖供应链风险，支持本地目录或 Git 仓库扫描，输出 PASS/WARN/FAIL 结论及修复建议
✎ 把代码审查、漏洞扫描和合规检查串成一条线，帮团队更早发现风险，做安全治理更省心。
相关 MCP 服务
by Sentry
搜索和分析 Sentry 错误报告，辅助调试。
✎ 把零散的 Sentry 错误报告变成可检索线索，帮你在海量报错里更快定位线上故障，排障调试明显省时。
by sinewaveai
为 AI agents 提供安全层：拦截 prompt injection、识别伪造 packages，并扫描漏洞风险。
✎ 给 AI Agent 补上关键安全层，能拦截 prompt 注入、识别伪造包并扫描漏洞风险，把防护前置更省心。
by pantheon-security
强化安全性的 NotebookLM MCP，集成 post-quantum encryption，提升数据防护能力。
相关资讯
MemPrivacy提出了一种在边缘设备上识别敏感词、替换为结构化占位符，再在云端处理记忆、本地恢复原始值的方法，实现了隐私保护与记忆效用的平衡。在覆盖200用户、5.2万隐私实例的基准测试中，该方法在隐私提取上超越GPT-5.2和Gemini-3.1-Pro，并将效用损失控制在1.6%以内。这项工作为边缘-云环境中安全性、实用性和用户透明度的部署提供了新思路。
OncoAgent是一个开源、隐私保护的肿瘤学临床决策支持系统。它采用双阶微调LLM架构（9B快速模型和27B深度推理模型）、8节点LangGraph多智能体拓扑、四级校正RAG管道和三重反射安全验证器。项目在AMD Instinct MI300X上通过QLoRA微调，序列打包使全数据集微调仅需50分钟，速度提升56倍。
本文介绍了 OpenAI Privacy Filter 模型的核心能力，并通过三个实战应用（文档隐私探索器、图片匿名化工具、智能脱敏粘贴板）展示了如何结合 gradio.Server 搭建端到端的 PII 检测与脱敏系统。重点分析了每种场景下模型负责什么、后端框架负责什么，以及如何通过 FastAPI 路由分离计算密集型任务与静态前端服务。