thanhnvandClaude Opus 4.8
36a4812ef3
Standard production layout: the OKR app (was nested under AINative_OKR_CASAN5/) is now
the repository root. No more wrapper directory.
- Promote AINative_OKR_CASAN5/* -> repo root (backend/ frontend/ packages/ apps/
.specify/ docs/ infra/ nginx/ scripts/ + configs). Merge tool dirs: .gitea (kept the
active deploy ci.yml, added harness-ci.yml + runbooks), .claude (agents/commands +
launch.json), .github moved up.
- Remove redundant: 00_SUBMISSION_PACKAGE, scattered root notes (FPT_CASAN_Full.md,
tu-tuong-casan.md, casan-tu-sinh..., casan_harness_assessment.md, source-review...,
README_CASAN5_REFINED.md), casan-next-plans/ and optimize-docs/ (competition/planning
artifacts — roadmap + design history preserved in git log / commit messages).
- Update all references to the old layout:
- .gitea/workflows/{ci,harness-ci}.yml, .github/workflows/{ci,deploy}.yml:
working-directory .; drop AINative_OKR_CASAN5/ prefix; .specify/{tests,scripts}
-> packages/casan-harness/... (.specify/logs state kept)
- .claude/launch.json, .gitea/*-runbook.md: path prefixes
- CLAUDE.md, README.md: docs/input -> apps/okr/domain/input
- policy-bundle.yaml: 8 policy paths -> packages/casan-harness/...; manifest re-signed
- secrets-scan.sh: fixture excludes -> new package/domain paths.
Full gate from the new root: PASS=64 FAIL=0 SKIP=3.
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 |