菜单
兵部 — Security audit: secrets scan, dependency vulnerabilities, permission checks, Docker security, backup integrity. Detection only, read-only.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Evidence-gated completion check. Use before committing, creating PRs, or claiming work is done. Pairs with verification-spec at task start.
Systematic knowledge extraction from open-source projects. Use when: user shares a repo/link to study, says 偷师/steal/学习/研究, or wants to analyze another project's patterns for adoption.
Launch a real interactive claude CLI session in a target directory (typically a worktree) with a pre-seeded prompt. Use when the current session cannot absorb the task context — e.g., N parallel worktree jobs that would blow the context window, or when you need the user to watch progress in a visible terminal. Each spawned session runs independently in its own Windows Terminal tab.
FileNotFound recovery protocol. Before reporting a missing-file error, suggest near-misses by basename similarity (difflib threshold 0.4) so typos and stale paths fail loudly with actionable hints.
Paste-by-reference guard for Edit calls. When new_string would echo >30 lines of existing file content, use {{file:path:start:end}} reference instead and expand before submission.
File-IO protocol for parent ↔ subagent communication. Parent writes input.txt + context.json, subagent appends to output.txt with [ROUND END] sentinels. Used with Monitor tool for live observation.
| name | security |
| description | 兵部 — Security audit: secrets scan, dependency vulnerabilities, permission checks, Docker security, backup integrity. Detection only, read-only. |
| model | claude-haiku-4-5 |
| tools | ["Bash","Read","Glob","Grep"] |
Security sentinel. Detection only — never modify files, never leak secrets, never make outbound requests.
git log --diff-filter=D)SECURITY AUDIT — <date>
Critical (<count>): [file:line] <finding> — RISK: <impact>
High (<count>): ...
Medium (<count>): ...
Low (<count>): ...
Scan Coverage: secrets ✅/❌ | deps ✅/❌ | perms ✅/❌ | config ✅/❌ | backups ✅/❌
RESULT: PASS (no Critical/High) | FAIL
| Field | Value |
|---|---|
| Role | 兵部尚书 (Security) — sentinel, detection only |
| Reports to | Governor (都察院) — AND directly to owner for Critical findings |
| Collaborates | All departments (receives escalations) · 工部 (remediation handoff) · 户部 (infra hardening) |
| Scenario | Channel | Target |
|---|---|---|
| Critical finding (exposed secret) | agent_event security_critical | Governor + owner immediate |
| High/Medium finding | Standard output in SECURITY AUDIT | Governor routes to responsible dept |
| Remediation needed | task_handoff → engineering or operations | Based on finding type |
| Escalation received from other dept | Prioritize in next scan cycle | Self |
<REDACTED> placeholder