find-bugs – skill Bảo mật cho agent AI
Tìm lỗi, lỗ hổng bảo mật và vấn đề chất lượng code trong các thay đổi của nhánh cục bộ. Dùng khi được yêu cầu review thay đổi, tìm lỗi, review bảo mật hoặc kiểm tra code trên nhánh hiện tại.
Cài skill find-bugs bằng một lệnh
Chọn công cụ bạn đang dùng, copy lệnh và dán vào terminal. Skill sẽ nằm trong thư mục skills của công cụ đó và sẵn sàng dùng ở phiên làm việc tiếp theo.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/find-bugs-00017.tgz | tar xz -C ~/.claude/skills
Gọi trong Claude Code: /find-bugs – rồi mô tả công việc bạn muốn làm.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/find-bugs-00017.tgz | tar xz -C ~/.codex/skills
Gọi trong Codex: $find-bugs – rồi mô tả công việc bạn muốn làm.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/find-bugs-00017.tgz | tar xz -C ~/.hermes/skills
Gọi trong Hermes Agent: /find-bugs – rồi mô tả công việc bạn muốn làm.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/find-bugs-00017.tgz | tar xz -C ~/.deepcode/skills
Gọi trong DeepSeek: /find-bugs – rồi mô tả công việc bạn muốn làm.
Nội dung SKILL.md
Nội dung SKILL.md gốc bằng tiếng Anh.
Find Bugs
Review changes on this branch for bugs, security vulnerabilities, and code quality issues.
When to Use
- You need a review focused on bugs, security issues, or risky code changes.
- The task involves auditing the current branch diff rather than implementing new behavior.
- You want a structured review process with checklist-driven verification against changed files.
Phase 1: Complete Input Gathering
1. Establish the requested base and head as verified commit SHAs. Check the remote/default branch if needed; do not assume a stale local branch is current. Read the full branch diff with git diff "$BASE_SHA...$HEAD_SHA" --, using validated refs in separately quoted arguments. Include staged and unstaged changes when they are in scope; preserve the checkout.
2. If output is truncated, read each changed file individually until you have seen every changed line
3. List all files modified in this branch before proceeding
Phase 2: Attack Surface Mapping
For each changed file, identify and list:
- All user inputs (request params, headers, body, URL components)
- All database queries
- All authentication/authorization checks
- All session/state operations
- All external calls
- All cryptographic operations
Phase 3: Security Checklist (check EVERY item for EVERY file)
- [ ] Injection: SQL, command, template, header injection
- [ ] XSS: All outputs in templates properly escaped?
- [ ] Authentication: Auth checks on all protected operations?
- [ ] Authorization/IDOR: Access control verified, not just auth?
- [ ] CSRF: State-changing operations protected?
- [ ] Race conditions: TOCTOU in any read-then-write patterns?
- [ ] Session: Fixation, expiration, secure flags?
- [ ] Cryptography: Secure random, proper algorithms, no secrets in logs?
- [ ] Information disclosure: Error messages, logs, timing attacks?
- [ ] DoS: Unbounded operations, missing rate limits, resource exhaustion?
- [ ] Business logic: Edge cases, state machine violations, numeric overflow?
Phase 4: Verification
For each potential issue:
- Check if it's already handled elsewhere in the changed code
- Search for existing tests covering the scenario
- Read surrounding context to verify the issue is real
Phase 5: Pre-Conclusion Audit
Before finalizing, you MUST:
1. List every file you reviewed and confirm you read it completely
2. List each applicable checklist item as a finding, verified within the reviewed scope, not applicable, or unverified; absence of a finding is not proof of security
3. List any areas you could NOT fully verify and why
4. Only then provide your final findings
Output Format
Prioritize: security vulnerabilities > bugs > code quality
Skip: stylistic/formatting issues
For each issue:
- File:Line - Brief description
- Severity: Critical/High/Medium/Low
- Problem: What's wrong
- Evidence: Concrete trigger, reachable path and observed or reasoned impact; missing tests alone do not prove a bug
- Fix: Concrete suggestion
- References: OWASP, RFCs, or other standards if applicable
If you find nothing significant, say so - don't invent issues.
For a review-only request, report findings without changing code. An explicit combined review-and-fix request authorizes scoped repairs and verification; preserve the distinction between findings and completed fixes.
Example
User request:
> Review the current branch diff for real bugs, security issues, and regressions, citing exact files and lines.
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Skill liên quan
- firebase – Firebase cung cấp backend hoàn chỉnh chỉ trong vài phút: auth, cơ sở dữ liệu, storage…
- firewall-config – Cấu hình iptables, nftables và cloud firewall. Triển khai phân vùng mạng và lọc lưu…
- firmware-analyst – Chuyên gia phân tích firmware, chuyên về hệ thống nhúng, bảo mật IoT và reverse…
- firmware-pentest – Kiểm thử xâm nhập firmware theo quy trình chín giai đoạn OWASP FSTM: trích xuất, tự động…
- fixing-accessibility – Kiểm tra và sửa lỗi khả năng truy cập HTML, gồm nhãn ARIA, điều hướng bàn phím, quản lý…
- fixing-metadata – Kiểm tra và sửa metadata HTML gồm tiêu đề trang, meta description, URL canonical, thẻ…
- security-guidance – Hook PreToolUse cho Claude Code phát hiện anti-pattern bảo mật. Bắt 12 rủi ro bảo mật…
- security-pen-testing – Dùng khi người dùng yêu cầu kiểm tra bảo mật, pen test, quét lỗ hổng, kiểm tra OWASP Top…