agentCLAWHUBUnverified
Huo15 Openclaw Security Review
对当前分支的 pending changes 做安全评审，命中密钥泄露 / SQL 注入 / XSS / SSRF / 权限绕过 / 危险依赖 六大类漏洞后出分级报告，再在用户批准下修复。用于 PR 合并前、对外开源前、线上事故后复盘。触发词：安全评审、security review、漏洞检查、密钥扫描、我的代码... Skill: Huo15 Openclaw Security Review Owner: zhaobod1 Summary: 对当前分支的 pending changes 做安全评审，命中密钥泄露 / SQL 注入 / XSS / SSRF / 权限绕过 / 危险依赖 六大类漏洞后出分级报告，再在用户批准下修复。用于 PR 合并前、对外开源前、线上事故后复盘。触发词：安全评审、security review、漏洞检查、密钥扫描、我的代码... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-24T14:34:44.651Z | user 首发 — 六类漏洞矩阵（密钥/注入/XSS/SSRF/权限/依赖）+ CVSS-like 四档 + CWE 对照 Archive index: Archive v1.0.0: 3 files, 4972 bytes Files: skil
OpenClaw
Rank
62
Safety
84
Downloads
966
Updated
Oct 12, 2026
Version
1.0.0
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 966 downloads reported by the source. Last updated 10/12/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 12, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 12, 2026
- Adoption signal
- 966 downloadsadoption · observed Oct 12, 2026
- Latest release
- 1.0.0release · observed Apr 24, 2026
- Handshake status
- UNKNOWNsecurity
What changed
Newest first. Only changes that point at a source are listed.
Release 1.0.0release
首发 — 六类漏洞矩阵（密钥/注入/XSS/SSRF/权限/依赖）+ CVSS-like 四档 + CWE 对照
Observed Apr 24, 2026 · source
Install and run
Setup complexity: low.
clawhub skill install s17f6q72skfgyjycm2frgdc8dn83v5mk:huo15-openclaw-security-review- Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-zhaobod1-huo15-openclaw-security-review/snapshot"
Run-check
$0.02 USD1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.
Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.
Documentation
CLAWHUB
6,976 characters of source documentation, loaded on request.
Extracted files
3 files captured from the source.
SKILL.md
---
name: huo15-openclaw-security-review
displayName: 火一五安全评审技能
description: 对当前分支的 pending changes 做安全评审，命中密钥泄露 / SQL 注入 / XSS / SSRF / 权限绕过 / 危险依赖 六大类漏洞后出分级报告，再在用户批准下修复。用于 PR 合并前、对外开源前、线上事故后复盘。触发词：安全评审、security review、漏洞检查、密钥扫描、我的代码有没有安全问题。
version: 1.0.0
aliases:
- 火一五安全评审
- 安全评审
- security review
- 安全审查
- 漏洞检查
- 密钥扫描
license: MIT
---
# 火一五安全评审技能 v1.0
> 六类漏洞矩阵 + 严重度分级 + 修复建议 — 青岛火一五信息科技有限公司
---
## 一、触发场景
- "帮我做个 security review"
- "这个 PR 有没有安全问题"
- "扫一下密钥泄露"
- "合并前做安全检查"
- "看看有没有 SQL 注入"
**范围**：默认 `git diff main...HEAD`（当前分支相对主干的全部改动）；用户可指定文件或 commit 范围。
**产出**：六类漏洞清单 + CVSS-like 严重度 + 每条修复建议 + 与 CWE 对照。
---
## 二、六类漏洞矩阵
### 类别 1：**敏感信息泄露（Secrets Leak）**
| 检查项 | 信号 |
|--------|------|
| 硬编码 API key / token | `/api[_-]?key\s*[:=]\s*["']([A-Za-z0-9_\-]{20,})["']/i` |
| 硬编码密码 / JWT secret | `password\s*[:=]\s*["'][^"']{6,}["']`、`jwt.*secret.*=` |
| `.env` 被提交 | `git log --all -- .env` 有记录 |
| 日志打印敏感字段 | `console\.log.*password`、`logger.*token` |
| 提交信息含密钥 | 扫 `git log --all --oneline` 的 message |
| Cloud 密钥格式特征 | AKIA...（AWS）/ ya29....（Google）/ ghp_... / npm_... |
### 类别 2：**注入（Injection）**
| 检查项 | 信号 |
|--------|------|
| SQL 拼接 | `` `SELECT ... ${...}` ``、`+ userInput +` |
| NoSQL 注入 | 未校验的 `$where` / `$regex` |
| 命令注入 | `exec(userInput)` / 模板字符串传 shell |
| 路径遍历 | `path.join(root, userInput)` 未 `path.normalize` + 边界校验 |
| LDAP / XPath / 模板注入 | 同样是拼接 |
### 类别 3：**跨站脚本（XSS）**
| 检查项 | 信号 |
|--------|------|
| `dangerouslySetInnerHTML` | React 直接接用户输入 |
| `innerHTML = userInput` | 原生 DOM |
| `v-html` 未过滤 | Vue |
| 邮件 / 短信模板直接插值 | 出站 XSS（钓鱼）|
| 未设 CSP header | 响应头缺失 |
### 类别 4：**服务端请求伪造（SSRF）**
| 检查项 | 信号 |
|--------|------|
| `fetch(userURL)` 无白名单 | 可被打到 169.254.169.254（云 metadata）|
| 允许 `file://` / `gopher://` 协议 | scheme 未校验 |
| DNS rebinding 窗口 | 二次解析 |
### 类别 5：**权限 / 认证绕过**
| 检查项 | 信号 |
|--------|------|
| 路由缺鉴权中间件 | Express / Next API route 裸接 |
| 水平越权 | 查询时没带 `userId = currentUser.id` |
| 直接对象引用（IDOR）| `GET /api/order/:id` 不校验归属 |
| JWT 不校验 signature | `jwt.decode` 代替 `jwt.verify` |
| 弱密码 / 默认账号残留 | grep `admin/admin123` |
### 类别 6：**危险依赖 / 供应链**
| 检查项 | 信号 |
|--------|------|
| 已知 CVE 依赖 | 建议用户跑 `npm audit` / `pnpm audit` |
| 从 git / tarball 装的依赖 | `package.json` 有 `git+https://...` |
| postinstall 脚本 | 可执行任意代码 |
| `typosquatting` 风险包 | `lodas` / `requets` 之类 |
---
## 三、工作流
1. **确定范围**
- 默认 `git diff main...HEAD --name-only`
- 允许用户指定：`commit 范围` / `特定文件` / `整个项目`
2. **只读扫描**
- Grep 六类信号模式
- Read 命中文件具体上下文
- **不执行 `npm audit`** — 返回命令让用户跑（避免长时间阻塞）
3. **严重度评级**
- 🔴 **Critical**：密钥已泄露到公共仓库 / 可远程代码执行 / 可绕过鉴权
- 🟠 **High**：SQL 注入 / XSS 反射点 / 可越权读
- 🟡 **Medium**：缺 CSP / 错误信息外泄 / 路径遍历有部分防御
- 🟢 **Low**：硬编码但仅 demo / 依赖有 low CVE
4. **产出报告**（见 §四）
5. **修复流程**
- 🔴 必须用户确认才改（防止误删 legit 用法）
- 🟠/🟡 列出修复建议，等用户决定
- 🟢 仅提示
---
## 四、报告模板
```markdown
## 安全评审报告 — <branch> vs main
**扫描范围**：12 个文件变更 · 扫描时间 2s
### 🔴 Critical（1 项，必须修）
1. **[Secrets]** `src/config.ts:18` — 硬编码 OpenAI AP_meta.json
{
"ownerId": "kn7byevkn40d6z4p7ghdb097z983tj33",
"slug": "huo15-openclaw-security-review",
"version": "1.0.0",
"publishedAt": 1777041284651
}skill-card.md
## Description: Reviews pending code changes for common security issues, including secrets exposure, injection, XSS, SSRF, authorization bypass, and vulnerable dependencies, then reports severity and suggested fixes. This skill is ready for commercial/non-commercial use. ## Publisher: [zhaobod1](https://clawhub.ai/user/zhaobod1) ### License/Terms of Use: MIT-0 ## Use Case: Developers and code reviewers use this skill before merges, open-source releases, or incident reviews to scan scoped code changes and receive a prioritized security report. ### Deployment Geography for Use: Global ## Known Risks and Mitigations: Risk: The skill may read code diffs and surrounding file context that include secrets or sensitive implementation details. Mitigation: Invoke it with an explicit branch, file list, or commit range when scope matters, and review reports for accidental sensitive disclosure. Risk: Security fix suggestions can change application behavior or remove legitimate code when applied too broadly. Mitigation: Require user approval before edits and review proposed patches before merging. ## Reference(s): - [ClawHub skill page](https://clawhub.ai/zhaobod1/skills/huo15-openclaw-security-review) - [Publisher profile](https://clawhub.ai/user/zhaobod1) ## Skill Output: **Output Type(s):** [analysis, markdown, code, shell commands, guidance] **Output Format:** [Markdown security review report with file references, severity ratings, CWE mappings, suggested fixes, and optional shell commands for user-run checks] **Output Parameters:** [1D] **Other Properties Related to Output:** [May propose code changes only after user approval; avoids printing full secrets in reports.] ## Skill Version(s): 1.0.0 (source: server release evidence and skill frontmatter) ## Ethical Considerations: Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
Github ReposUpdated 4d agoRank 70
AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
OPENCLAW
Github ReposUpdated 6mo agoRank 70
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
OPENCLAW
Machine-readable data
The same record, as JSON, for agents and crawlers.
- Card JSON
- Facts JSON
- Snapshot JSON
- Contract JSON
- Trust JSON
- Changes JSON
- Warnings JSON
- Seen by JSON
- Disagreements JSON
- Proof JSON
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/zhaobod1/skills/huo15-openclaw-security-review",
"sourceUrl": "https://clawhub.ai/zhaobod1/skills/huo15-openclaw-security-review",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-12T00:43:14.668Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-zhaobod1-huo15-openclaw-security-review/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-zhaobod1-huo15-openclaw-security-review/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-12T00:43:14.668Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "966 downloads",
"href": "https://clawhub.ai/zhaobod1/huo15-openclaw-security-review",
"sourceUrl": "https://clawhub.ai/zhaobod1/huo15-openclaw-security-review",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-12T00:43:14.668Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.0.0",
"href": "https://clawhub.ai/zhaobod1/huo15-openclaw-security-review",
"sourceUrl": "https://clawhub.ai/zhaobod1/huo15-openclaw-security-review",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-04-24T14:34:44.651Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-zhaobod1-huo15-openclaw-security-review/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-zhaobod1-huo15-openclaw-security-review/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.0.0",
"description": "首发 — 六类漏洞矩阵（密钥/注入/XSS/SSRF/权限/依赖）+ CVSS-like 四档 + CWE 对照",
"href": "https://clawhub.ai/zhaobod1/huo15-openclaw-security-review",
"sourceUrl": "https://clawhub.ai/zhaobod1/huo15-openclaw-security-review",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-04-24T14:34:44.651Z",
"isPublic": true
}
]
}Record generated Oct 13, 2026.
For crawlers
This page is free to read. The run-check above is the only paid part, and it answers HTTP 402 until it is paid. Everything else here is public.
- One record, as JSON: card, facts, snapshot, contract, trust, changes, warnings, seen by, disagreements, proof.
- Every agent, one feed: /.well-known/ai-catalog.json
- What this site sells, and the price: /.well-known/x402
- Paid run-check: /api/v1/agents/clawhub-zhaobod1-huo15-openclaw-security-review/run-check