Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add qinye6/pi-ccg --skill verify-securitygit clone --depth 1 https://github.com/qinye6/pi-ccgWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/qinye6/pi-ccg/verify-security)<a href="https://agentmods.dev/skills/qinye6/pi-ccg/verify-security"><img src="https://agentmods.dev/badge/skills/qinye6/pi-ccg/verify-security.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.01097 |
| Opus 5 | $0.00039 | $0.00549 |
| Sonnet 5 | $0.00016 | $0.00219 |
| Haiku 4.5 | $0.00008 | $0.00110 |
Grade A, and why
verify-security scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
eval(), exec(), os.system() This is a copy
100% identical to verify-security — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚖ 校验关卡 · 安全校验
核心原则
安全即道基，破则劫败
安全决策必须可追溯
Critical/High 问题必须修复后才能交付
自动扫描
运行安全扫描脚本（跨平台）：
# 在 skill 目录下运行
node scripts/security_scanner.js <扫描路径>
node scripts/security_scanner.js <扫描路径> -v # 详细模式
node scripts/security_scanner.js <扫描路径> --json # JSON 输出
node scripts/security_scanner.js <扫描路径> --exclude vendor # 排除目录
检测范围
自动检测的漏洞类型
| 类别 | 检测项 | 严重度 |
|---|---|---|
| 注入 | SQL 注入、命令注入、代码注入 | 🔴 Critical |
| 敏感信息 | 硬编码密钥、AWS Key、私钥 | 🔴 Critical |
| XSS | innerHTML、dangerouslySetInnerHTML | 🟠 High |
| 反序列化 | pickle.loads、yaml.load | 🟠 High |
| 路径遍历 | 未验证的文件路径操作 | 🟠 High |
| SSRF | 未验证的 URL 请求 | 🟠 High |
| XXE | 不安全的 XML 解析 | 🟠 High |
| 弱加密 | MD5、SHA1 用于安全场景 | 🟡 Medium |
| 不安全随机 | random 模块用于安全场景 | 🟡 Medium |
| 调试代码 | console.log、print、debugger | 🔵 Low |
文档层面检查
安全相关代码必须在 DESIGN.md 中记录：
- 威胁模型 — 防御哪些攻击
- 安全决策 — 为何选择此方案
- 安全边界 — 信任边界在哪里
- 已知风险 — 接受了哪些风险
危险模式速查
Python
# 🔴 危险 - 触犯道基
eval(), exec(), os.system()
subprocess(..., shell=True)
pickle.loads(), yaml.load()
cursor.execute(f"SELECT * FROM t WHERE id = {id}")
# ✅ 安全替代 - 道基稳固
ast.literal_eval()
subprocess([...], shell=False)
yaml.safe_load()
cursor.execute("SELECT * FROM t WHERE id = %s", (id,))
JavaScript
// 🔴 危险 - 触犯道基
eval(), innerHTML, document.write()
new Function(userInput)
// ✅ 安全替代 - 道基稳固
JSON.parse(), textContent
模板引擎自动转义
Go
// 🔴 危险 - 触犯道基
exec.Command("sh", "-c", userInput)
template.HTML(userInput)
// ✅ 安全替代 - 道基稳固
exec.Command("cmd", args...)
html/template 自动转义
校验流程
1. 运行 security_scanner.js 自动扫描
2. 分析扫描结果，按严重度排序
3. 检查安全决策是否有文档记录
4. 输出安全校验报告
5. Critical/High 问题必须修复后才能交付
自动触发时机
| 场景 | 触发条件 |
|---|---|
| 新建模块 | 模块创建完成时 |
| 安全相关变更 | 涉及认证、授权、加密、输入处理 |
| 攻防任务 | 红队/蓝队任务完成时 |
| 重构完成 | 重构任务完成时 |
| 提交前 | 代码提交前检查 |
校验报告格式
## 安全校验报告
✓ 通过 | ✗ 未通过
- 🔴 Critical: N
- 🟠 High: N
- 🟡 Medium: N
- 🔵 Low: N
### 发现问题
| 文件 | 行号 | 类型 | 严重度 | 描述 |
|------|------|------|--------|------|
| ... | ... | ... | ... | ... |
### 结论
可交付 / 需修复后交付
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 144 lines · 78 tokens per session scan A 2889587c53d1
verify-security is a skill published in the GitHub repository qinye6/pi-ccg (10 stars, last pushed 13d ago), licensed MIT. It adds 78 tokens to every session and 1,097 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 100% identical to verify-security, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…