skills/security-review/SKILL.md
Security review via Codex MCP. Use when: OWASP Top 10 audit, dependency vulnerability check, security-sensitive changes. Not for: code review (use codex-code-review), test review (use test-review). Output: security findings + audit report.
npx skillsauth add sd0xdev/sd0x-dev-flow security-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
codex-code-review)test-review)| Command | Purpose | When |
| ----------------- | ------------------------ | ----------------------- |
| /codex-security | OWASP Top 10 audit | Security-sensitive code |
| /dep-audit | Dependency security audit | Periodic / PR |
/codex-securityDetermine scope → Collect changes → Codex OWASP review → Findings + Gate → Loop if Must fix
Parse --scope from arguments, default to src/.
Priority order:
git diff HEAD -- <scope> | head -1500git diff HEAD~5..HEAD -- <scope> | head -1500Glob("**/*{auth,login,password,token,secret,key,credential}*")First review: mcp__codex__codex with OWASP prompt. See references/codex-prompt-security.md.
Config: sandbox: 'read-only', approval-policy: 'never'
Save the returned threadId.
Loop review: mcp__codex__codex-reply with re-review template. See references/codex-prompt-security.md.
Organize results into findings summary table + detailed findings + gate.
| Code | Category | Check Focus | | ---- | ------------------ | ------------------------------------ | | A01 | Broken Access Ctrl | IDOR, permission bypass, CORS | | A02 | Crypto Failures | Sensitive data encryption, weak crypto | | A03 | Injection | SQL/NoSQL/Cmd Injection | | A04 | Insecure Design | Rate Limiting, business logic | | A05 | Misconfiguration | Debug mode, default passwords | | A06 | Vulnerable Comp | Known vulnerable dependencies | | A07 | Auth Failures | Brute force, session, weak passwords | | A08 | Integrity Failures | Deserialization, CI/CD | | A09 | Logging Failures | Sensitive data in logs, auditing | | A10 | SSRF | URL validation, internal network access |
⚠️ @CLAUDE.md auto-loop: fix → re-review → ... → ✅ PASS ⚠️
⛔ Must fix → fix P0 issues → /codex-security --continue <threadId> → repeat until ✅ Mergeable.
Max 3 rounds. Still failing → report blocker.
references/codex-prompt-security.mdreferences/examples.mdInput: /codex-security --scope src/controller/
Action: OWASP Top 10 check → output issues + Gate
Input: /dep-audit --level high
Action: npm audit → filter high/critical → output report
documentation
Rewrite the previous reply in Traditional Chinese
development
Monitor GitHub Actions CI runs until completion. Use when: watching CI after push, checking build status, monitoring PR checks, waiting for CI completion, user says 'watch CI', 'check CI', 'CI status', 'monitor build', or /watch-ci. Not for: pushing code (use push-ci), creating PRs (use create-pr). Output: per-run verdict (pass/fail/timeout).
development
Verification loop — lint -> typecheck -> unit -> integration -> e2e
development
Research current code state then update corresponding docs, ensuring docs stay in sync with code.