跳到正文
cccskills
免费在 GitHub 公开

dev-security

Audit the code for vulnerabilities, leaked secrets and risky dependencies before it ships.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Dev Security - Security Audit

Delegate to Sentinel for comprehensive security review.

Philosophy

"Every line of code is guilty until proven innocent."

Flow

1. Context Gathering

# What changed?
git diff --name-only HEAD~10 2>/dev/null || git diff --name-only

# What's the scope?
ls -la

2. Invoke Sentinel

Delegate to Sentinel agent:

"Sentinel, security audit time.

Scope: {describe what changed or focus area}

Run your full checklist:
1. Secrets scan
2. Dependency audit
3. Injection vectors
4. Auth/authz review
5. Crypto check

Files changed: {list from git diff}

Be thorough. We're not shipping vulnerabilities."

3. Review Sentinel's Findings

Sentinel returns findings by severity:

  • CRITICAL: Must fix before merge
  • HIGH: Should fix before merge
  • MEDIUM: Should fix soon
  • LOW: Consider fixing

4. Action on Findings

If CRITICAL or HIGH found:

Security audit found issues:

CRITICAL:
- [Issue 1 with location and fix]

HIGH:
- [Issue 2 with location and fix]

Options:
1. Fix now (Bob will implement Sentinel's fixes)
2. Fix manually, run /dev-security again
3. Accept risk (requires explicit acknowledgment)
4. Get second opinion (run deeper audit)

If only MEDIUM/LOW:

Security audit passed with notes.

MEDIUM:
- [Issue with suggestion]

LOW:
- [Issue with suggestion]

These don't block shipping but should be tracked.
Add to backlog? (y/n)

If clean:

Security audit passed!

Sentinel says: "Huh. Someone actually read the OWASP guide. Respect."

Ready for:
- /dev-rc - Release candidate
- /dev-finish - Close the cycle

5. Log Results

If active dev-cycle session:

## Security Audit
- **Date**: {timestamp}
- **Status**: PASSED | PASSED_WITH_NOTES | FAILED
- **Critical**: 0
- **High**: 0
- **Medium**: 2
- **Low**: 1

### Findings
{Summary of what was found and resolved}

Focus Modes

Full Audit (default)

/dev-security

Everything: secrets, deps, code, config, infra

Quick Scan

/dev-security quick

Just the critical stuff: secrets, known CVEs, obvious injection

Specific Focus

/dev-security auth
/dev-security crypto
/dev-security deps
/dev-security secrets

Focus on one area for deeper review.

What Sentinel Checks

AreaWhatWhy
SecretsHardcoded keys, tokens, passwords#1 breach cause
DependenciesKnown CVEs, outdated packagesSupply chain attacks
InjectionSQL, XSS, command, path traversalOWASP Top 10
AuthBroken auth, missing authzGateway to everything
CryptoWeak algorithms, hardcoded keysData protection
ConfigExposed debug, permissive CORSMisconfiguration

Integration

With dev-cycle: Logs findings to session With dev-rc: Security must pass for release candidate With Bob: Implements fixes for findings With Sentinel: The security brain

When to Run

  • Before any PR
  • After implementing auth/authz
  • After adding new dependencies
  • After handling user input
  • After touching crypto
  • Before any release
  • When Sentinel whispers "trust nothing"

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Branch and commit conventions that keep an agent's work reviewable — one branch per task, main stays clean, nothing force-pushed.

中文简介正在准备中。当前显示原文说明。

ToruAI/toru-claude-agents152026年7月26日 更新

cc-docs

免费

Look up how Claude Code itself works — hooks, skills, subagents, MCP, plugins, settings — from the official docs, so answers come from the current spec instead of memory.

中文简介正在准备中。当前显示原文说明。

ToruAI/toru-claude-agents152026年7月26日 更新

Design better agents, skills and hooks for Claude Code, checking the current spec instead of guessing at fields.

中文简介正在准备中。当前显示原文说明。

ToruAI/toru-claude-agents152026年7月26日 更新

dev-cycle

免费

Run a feature end to end — scout the code, plan it, build it, and keep a session file so a closed terminal doesn't lose the thread.

中文简介正在准备中。当前显示原文说明。

ToruAI/toru-claude-agents152026年7月26日 更新

Close out a session — summarise what changed, capture what was learned, and prepare the commit.

中文简介正在准备中。当前显示原文说明。

ToruAI/toru-claude-agents152026年7月26日 更新

Hand over a spec and walk away — plans, builds, tests and audits on its own, stopping only at a real blocker.

中文简介正在准备中。当前显示原文说明。

ToruAI/toru-claude-agents152026年7月26日 更新

查看 ToruAI 的全部技能

报告此技能的问题