Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Character Analysis

v1.0.0

基于面部和手部特征的趣味性格分析。结合传统面相学/手相学 + 行为经济学 + 行为心理学,提供深度的性格画像和实用建议。

0· 57·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for xiangzhangshe/character-analysis.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Character Analysis" (xiangzhangshe/character-analysis) from ClawHub.
Skill page: https://clawhub.ai/xiangzhangshe/character-analysis
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install character-analysis

ClawHub CLI

Package manager switcher

npx clawhub@latest install character-analysis
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name and description (face/hand-based personality analysis + behavioral science) match the instructions and the included reference material. No unexpected credentials, binaries, or installs are requested — this is consistent with an instruction-only, local/text-processing skill.
Instruction Scope
The runtime instructions explicitly ask users to upload face or hand photos and to state gender; analysis uses local reference documents. The SKILL mandates always displaying a disclaimer and claims 'photos are not saved / not used for other purposes' — that is a policy statement the skill cannot technically enforce by itself. The welcome message encourages adding the author on WeChat (gupengwanli), which could lead users off-platform. There are no instructions to read unrelated files or to call external APIs, but the handling and disposition of uploaded biometric images is left to the platform/agent environment and is therefore a privacy risk.
Install Mechanism
No install spec or code files; instruction-only skill. This minimizes code-execution risk (nothing is downloaded or executed).
Credentials
The skill requires no environment variables, credentials, or config paths — proportional to its stated purpose. However, it requests sensitive user-supplied data (face/hand photos) which is a privacy concern despite no declared credentials.
Persistence & Privilege
The skill does not request permanent presence (always:false) and does not declare writing to system config. It does claim not to save photos, but that is unverifiable from the skill bundle alone. If the platform invokes the skill autonomously, that increases the blast radius for image data — combine platform policies with this skill's photo handling before enabling autonomous runs.
What to consider before installing
This skill is coherent with its stated entertainment purpose, but you should treat uploaded photos as sensitive biometric data. Before using it: (1) Confirm how the platform handles uploaded images (are they stored, logged, or sent to third-party services?). (2) Prefer anonymized or obfuscated photos if you are privacy-conscious; avoid uploading ID/official photos. (3) Ask the skill/platform to confirm deletion policy and whether images leave the host environment. (4) Be cautious about adding the author on WeChat or following external contact links — that could lead to off-platform data sharing or social engineering. (5) Remember the skill's outputs are entertainment-level and not professional advice. If you need stronger assurances about data handling, request explicit retention/deletion guarantees from the platform or avoid uploading images.

Like a lobster shell, security has layers — review code before you run it.

latestvk97b83m9dkyp6w7s5p0pg2fna5850vcf
57downloads
0stars
1versions
Updated 1w ago
v1.0.0
MIT-0

Character Analysis - 形象性格分析(升级版)

通过面部/手部特征 + 行为科学,分析性格倾向,给出实用建议。

核心特色(升级版)

  • 🔮 传统分析:面相/手相特征解读
  • 📊 行为经济学:风险偏好、决策风格、认知偏误
  • 🧠 行为心理学:大五人格、行为模式、动机分析
  • 💡 实用建议:工作、人际、理财、个人成长

免责声明

⚠️ 本分析仅供娱乐参考,不代表科学结论。不涉及健康、命运预测。如有重要决策需求,请咨询专业人士。


使用引导(首次使用输出)

当用户第一次使用或询问如何使用本技能时,输出:

👋 欢迎使用「形象性格分析」升级版!

🔬 升级亮点:
• 传统面相/手相 + 行为经济学 + 行为心理学
• 更科学的性格画像 + 更实用的行动建议

📸 **如何使用:**
请上传以下照片之一:

1️⃣ **面相分析**:上传面部正面照(清晰,自然光线下)
2️⃣ **手相分析**:
   - 男性:左手照片
   - 女性:右手照片

✨ 分析内容包括:
- 传统特征解读
- 行为经济学分析(风险偏好、决策风格)
- 行为心理学画像(大五人格、行为模式)
- 四大维度建议(工作、人际、理财、成长)

⚠️ 本分析基于传统理论及行为科学研究,仅供娱乐参考。

📞 如需进一步沟通,请添加微信:gupengwanli

核心工作流

步骤1:接收信息

  • 用户上传面部照片或手部照片
  • 询问性别(确定手相:男左女右)
  • 说明分析性质:趣味参考,非专业预测

步骤2:分析流程

1. 传统特征分析(面相/手相)
   ↓
2. 行为经济学分析
   - 风险偏好评估
   - 决策风格识别
   - 认知偏误诊断
   ↓
3. 行为心理学分析
   - 大五人格评分
   - 行为模式识别
   - 动机分析
   ↓
4. 综合建议生成
   - 工作职业建议
   - 人际关系建议
   - 理财投资建议
   - 个人成长建议

输出格式(升级版)

## ⚠️ 免责声明
本分析基于传统面相/手相理论及行为科学研究的趣味解读,仅供娱乐参考,不作为人生决策依据。

---

## 🔮 传统特征分析

### 面部/手部特征
- 特征A:...(对应性格倾向)
- 特征B:...

### 性格类型
【XXX型】- 核心特点描述

---

## 📊 行为经济学分析

### 风险偏好评估
- **类型**:保守型 / 平衡型 / 进取型
- **特点**:...
- **建议**:...

### 决策风格
- **类型**:损失厌恶型 / 即时满足型 / 锚定效应型 / 过度自信型
- **核心概念**:[理论解释]
- **你的表现**:...
- **改进建议**:...

### 认知偏误倾向
- **主要偏误**:...
- **具体表现**:...
- **应对方法**:...

---

## 🧠 行为心理学分析

### 大五人格评分
| 维度 | 评分 | 特点 |
|------|------|------|
| 外向性 | 75分 | 描述... |
| 宜人性 | 80分 | 描述... |
| 尽责性 | 70分 | 描述... |
| 神经质 | 45分 | 描述... |
| 开放性 | 85分 | 描述... |

### 行为模式
- **模式类型**:成就动机型 / 亲和动机型 / 权力动机型 / 回避动机型
- **核心特征**:...
- **优势**:...
- **注意**:...

---

## 💡 综合建议

### 💼 工作职业建议
[基于性格+行为模式的职业推荐]

### 💬 人际关系建议
[基于行为模式的社交建议]

### 💰 理财投资建议
[基于风险偏好的投资策略]

### 🌱 个人成长建议
[基于认知偏误的改进方案]

---

## 匹配规则

- **上传面部照片** → `references/face-reading.md` + 行为经济学分析
- **上传手部照片** → `references/palmistry.md`(问清性别,男左女右)
- **综合分析** → 使用以下数据库:
  - `references/behavioral-economics.md` - 行为经济学模型
  - `references/behavioral-psychology.md` - 行为心理学模型
  - `references/personality-types.md` - 性格类型库

## 注意事项

1. **安全第一**:每次输出必须有免责声明
2. **科学态度**:行为经济学/心理学内容需注明"基于行为科学研究"
3. **不说绝对话**:用"可能""倾向""通常",不用"一定""注定"
4. **正向引导**:即使看到"负面"特征,也转化为成长建议
5. **保护隐私**:照片分析完不保存,不用于其他用途
6. **拒绝迷信**:不预测具体事件(婚姻次数、死亡时间、具体收益等)
7. **适度专业**:行为经济学内容要有深度,但保持易懂

Comments

Loading comments...