thanhnvandClaude Opus 4.8
664bd1f00c
Physically move the pure-code subtrees out of .specify into the package, leaving compat symlinks at the old .specify/<dir> paths so every existing reference (internal CASAN_HARNESS_ROOT + external CI/docker/mjs) keeps resolving. Runtime state stays put. Moved (git mv): scripts/ tests/ security/ templates/ config/ governance/ memory/ .specify/<dir> -> packages/casan-harness/<dir> (+ .specify/<dir> symlink) Stays in .specify (state/governance/domain, handled later): logs/ agentops/ level5/ init-options.json traceability-map.json Python `.resolve()` self-location followed the compat symlink into packages and lost the app root; generate-casan-demo-context.py, generate-agentops-dashboard.py and dashboard-server.py now walk UP for the `.specify` state marker instead of a fixed parent depth (fixes "missing trace files" in run-casan4). Full gate: PASS=64 FAIL=0 SKIP=3 (CASAN_CI_STEP_TIMEOUT_SEC=1200 — track-a ~450s runs close to the 600s default and can tip over under load; this is timing variance, not a regression — it passed cleanly with headroom). Runtime log/audit artifacts kept unstaged. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2.4 KiB
2.4 KiB
🔐 Security Policy
Project: AINATIVE_OKR_CLAUDE_GHCP
1. Purpose
Tài liệu này định nghĩa chính sách bảo mật cho AI System nhằm:
- Ngăn chặn prompt injection
- Bảo vệ dữ liệu nhạy cảm (PII, secret)
- Kiểm soát hành vi của LLM/Agent
- Đảm bảo an toàn khi vận hành production
2. Scope
Áp dụng cho toàn bộ hệ thống:
- Prompt / LLM interaction
- Agent workflow
- Template generation (SpecKit)
- Script automation
- Logging & monitoring
3. Security Principles
- ✅ Zero Trust Input: Không tin bất kỳ input nào từ user
- ✅ Least Privilege: Tool/Agent chỉ có quyền tối thiểu
- ✅ Defense in Depth: nhiều lớp bảo vệ
- ✅ Auditability: mọi hoạt động phải log được
- ✅ Fail Safe: khi nghi ngờ → block hoặc require approval
4. Threat Model (OWASP LLM Top 10 based)
| Threat | Description |
|---|---|
| Prompt Injection | User cố override system |
| Data Leakage | Lộ thông tin nội bộ |
| Secret Exposure | Lộ API key / credential |
| Unsafe Tool Call | Agent thực thi hành động nguy hiểm |
| Hallucination Risk | Output sai nhưng có vẻ đúng |
5. Input Security Policy
5.1 Prompt Injection Protection
Block các pattern:
- "ignore previous instruction"
- "bypass system"
- "override policy"
Action
| Level | Action |
|---|---|
| High | Block |
| Medium | Require Approval |
| Low | Log |
5.2 PII Detection
Detect:
- Phone number
- Personal ID
- Address
Action
- Mask trước khi gửi LLM
- Log sự kiện
5.3 Secret Detection
Detect:
- API Keys
- Tokens
- Password
Action
- Block
- Alert system
- Không gửi vào LLM
6. Output Security Policy
6.1 Data Leakage Prevention
- Không output:
- nội dung confidential
- internal system prompt
- hidden instruction
6.2 Output Filtering
| Type | Action |
|---|---|
| PII | Mask |
| Secret | Remove |
| Unsafe content | Block |
| Hallucination risk | Flag |
7. Tool Security Policy
7.1 Tool Access Control
| Tool | Permission |
|---|---|
| Read File | Allow |
| Write File | Restricted |
| Delete File | Require Approval |
| External API | Whitelist only |