ccpa-audit
Skill0 starsChanged 3 months agoMITView on GitHub
CCPA Compliance Audit — California Consumer Privacy Act (CCPA, Cal. Civ. Code §1798.100 et seq.) & CPRA amendment.
- Reads credentials
In this repository11 other files it gives its agents.
- ccpa-checkSkill
- ccpa-complianceSkill
- ccpa-guardSkill
- coppa-checkSkill
- coppa-guardSkill
- gdpr-auditSkill
- gdpr-checkSkill
- gdpr-complianceSkill
- gdpr-guardSkill
- hipaa-checkSkill
- hipaa-guardSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 36
Check items are served from the cloud rule library (always current).
- Distinctive: line 90
When a user asks for a CCPA 合规深度审计:
- Very specific: line 91
Run --non-interactive to preview the 24 items (no Key needed).
- Very specific: line 92
If the user wants a scored report, point them to the web account center to get a free Key, then run the full 审计 (the Key is read from …
- Very specific: line 98
Where data goes: Check items are fetched from, and your answers are scored by, the CQDev cloud at https://compliancehub.cn (the operator's …
- Very specific: line 109
Always confirm the destination is compliancehub.cn before running a scored check.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
🔒 CCPA Compliance Audit (CCPA 合规深度审计) — Free, Cloud-Scored
Overview
CCPA 合规深度审计 is a free 审计 based on 加州消费者隐私法案(CCPA)及 CPRA 修正案. It covers 20 core items. Scoring runs on the CQDev cloud compliance engine.
How it works (free + cloud)
⚠️ Your answers leave this machine. When you run a scored 审计, your responses are transmitted to the CQDev cloud at
compliancehub.cnfor scoring. The free--non-interactivepreview fetches the latest check items from the cloud rule library but transmits NO answers; it falls back to the bundled item set if the network is unavailable.
- The skill is free to install.
- Check items are served from the cloud rule library (always current).
- Scoring + quota are computed in the cloud; you get a professional report locally.
- A free API Key (100 calls) is required for scoring. Get one in seconds at the web account center.
What it checks (24 items)
| # | Check | Authority |
| 1 | 知情权 | CCPA §1798.100 |
| 2 | 删除权 | CCPA §1798.105 |
| 3 | 选择退出权 | CCPA §1798.120 |
| 4 | 非歧视原则 | CCPA §1798.125 |
| 5 | 更正权 | CPRA §1798.106 |
| 6 | 请求验证 | CCPA §1798.145(i) |
| 7 | 授权代理人 | CCPA §1798.130(a)(2) |
| 8 | 收集通知 | CCPA §1798.100(b) |
| 9 | 个人信息类别 | CCPA §1798.140 |
| 10 | 隐私政策 | CCPA §1798.130 |
| 11 | 年度披露 | CCPA §1798.130(a)(5) |
| 12 | 数据最小化 | CPRA §1798.100(b) |
| 13 | 敏感个人信息(CPRA) | CPRA §1798.140(ae) |
| 14 | 限制敏感PI使用 | CPRA §1798.121 |
| 15 | 留存期限 | CPRA §1798.100(a)(3) |
| 16 | 服务提供商义务 | CCPA §1798.140(ag) |
| 17 | 第三方共享 | CCPA §1798.115 |
| 18 | 合同审计权 | CCPA §1798.140(ag)(3) |
| 19 | 自动化决策 | CPRA §1798.185(a)(16) |
| 24 | 未成年人数据 | CCPA §1798.120(c) |
| 21 | 暗模式/选择对称性 | CCPA §1798.140(ad) |
| 22 | 员工/求职者数据 | CCPA §1798.100 (HR context) |
| 23 | 安全义务 | CCPA §1798.150(a)(1) |
| 24 | 高风险评估/网络安全审计(前瞻) | CPPA 2025 Rules (Risk Assessments / Cyber Audits) |
Usage
💡 交互提示:逐项作答时可直接输入中文(是 / 否 / 不适用),输入
?可查看该项的合规建议
Free preview (no Key)
python3 scripts/ccpa-audit.py --non-interactiveGet a free API Key (web, then hand it to this skill)
- Open the account center and register (human check is browser-only): https://compliancehub.cn/account.html?skill=ccpa-audit
- Copy the Key, then give it to this skill (pick one):
export COMPLIANCEHUB_API_KEY=<网页显示的 Key>或用编辑器手动创建密钥文件 ~/.config/compliancehub/ccpa-audit.key(权限 600)并粘贴 Key。
Full 审计 + report
python3 scripts/ccpa-audit.py --format html -o ccpa-audit-report.htmlAgent guide
When a user asks for a CCPA 合规深度审计:
- Run
--non-interactiveto preview the 24 items (no Key needed). - If the user wants a scored report, point them to the web account center to get a free Key, then run the full 审计 (the Key is read from COMPLIANCEHUB_API_KEY or ~/.config/compliancehub/ccpa-audit.key).
Security & data handling
- No account creation / no credentials collected: This skill never prompts for or transmits your email/password,
and it never registers accounts. In preview mode (
--non-interactive) it only reads the public rule library and sends NO answers; nothing about your compliance status persists across sessions. - Where data goes: Check items are fetched from, and your answers are scored by, the CQDev cloud at
https://compliancehub.cn(the operator's official endpoint). Scoring transmits only your item answers and the free API Key (as a Bearer token). - API Key (you provide it): obtained from the web account center and supplied via the
COMPLIANCEHUB_API_KEYenvironment variable or~/.config/compliancehub/ccpa-audit.key(0600, outside the skill folder). The skill reads the Key; it does not write accounts or collect credentials. - No shell execution: stdlib only (
urllib,json,ssl); no shell, no external binaries. - Not a rogue/autonomous agent: The stored files are an ordinary API key file (0600) and a random
anonymous-trial anon_id (
~/.config/compliancehub/ccpa-audit.anon_id, 0600, no personal data) — not auto-start, session, or background processes. No compliance answers are stored locally. - Preview mode:
--non-interactivefetches the public check items from the cloud rule library but sends NO answers; it falls back to the bundled item set if the network is unavailable. - Always confirm the destination is
compliancehub.cnbefore running a scored check.
Legal disclaimer
This tool provides general compliance guidance only and is not legal advice. Consult qualified counsel.
License
MIT.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

