Skill Trust Decision

psychology-analysis

Name: psychology-analysis Trust Review Report
Item: psychology-analysis
Rating: 58
Author: ClawSafe

心理健康分析工具包含多项未声明的敏感操作（本地数据库、凭证存储、环境变量读取），存在文档欺骗风险，但核心功能为合法的视频分析服务。

Install decision first Source: ClawHub Scanned: 14 days ago

Files 31

Artifacts 12

Violations 4

Findings 4

Most direct threat evidence

Why this conclusion was reached

1/4 dimensions flagged

Block

Declared vs actual capability

4 undeclared or violating capabilities were inferred.

Review

Hidden execution and egress

12 lower-risk artifacts were extracted and still need context.

Pass

Attack chain and severe findings

There is no explicit malicious chain in the report.

Pass

Dependencies and supply chain hygiene

Dependencies are present but no obvious high-risk issue stands out.

What drove the risk score up

文档-行为差异 +20

SKILL.md未声明SQLite数据库操作、data/smyx-api-key.txt文件读取、凭证存储等敏感行为

环境变量读取 +10

代码读取OPENCLAW_SENDER_OPEN_ID等环境变量，未在文档中声明

数据库操作 +10

创建并操作SQLite数据库存储用户token/open_token，未声明

合法功能无越权 +-5

核心视频分析功能正常，无RCE、凭证外泄等恶意行为

Most important evidence

Medium Doc Mismatch

未声明的本地数据库操作

技能在 data 目录下创建 SQLite 数据库 smyx-common-claw.db，存储用户的 username、token、open_token 等敏感凭证。SKILL.md 未声明此数据库操作。

skills/smyx_common/scripts/dao.py:68

在 SKILL.md 的资源索引部分声明数据库操作及其用途

Medium Doc Mismatch

未声明的敏感文件读取

OpenIdUtil 从 data/smyx-api-key.txt 读取 API 密钥，SKILL.md 未声明此文件访问行为。

skills/smyx_common/scripts/util.py:237

在文档中说明凭证文件的读取方式和安全存储

Medium Doc Mismatch

未声明的环境变量读取

ConstantEnum.init() 读取 OPENCLAW_SENDER_OPEN_ID、OPENCLAW_SENDER_USERNAME、FEISHU_OPEN_ID 等环境变量，SKILL.md 未声明。

skills/smyx_common/scripts/config.py:107

在文档中声明所需的环境变量及其用途

Low Sensitive Access

工作区路径检测算法

AgentContextUtil.detect_current_agent_workspace() 实现了复杂的工作区检测逻辑，涉及 agent_id 追踪，代码复杂度过高但无明显恶意。

skills/smyx_common/scripts/util.py:109

简化工作区检测逻辑，减少攻击面

Declared capability vs actual capability

Filesystem Block

Declared NONE

→

Inferred READ

skills/smyx_common/scripts/util.py:237 smyx-api-key.txt

Filesystem Block

Declared NONE

→

Inferred WRITE

skills/smyx_common/scripts/dao.py:68 SQLite数据库创建

Environment Block

Declared NONE

→

Inferred READ

skills/smyx_common/scripts/config.py:107 环境变量读取

Database Block

Declared NONE

→

Inferred WRITE

skills/smyx_common/scripts/dao.py 完整的CRUD操作

Network Pass

Declared READ

→

Inferred READ

scripts/psychology_analysis.py API调用

Suspicious artifacts and egress

Medium External URL

https://lifeemergence.com/sample.html

SKILL.md:37

Medium External URL

https://clawhub.ai/user/smyx-sunjinhui

skill-card.md:9

Medium External URL

https://clawhub.ai/smyx-sunjinhui/skills/smyx-psychology-analysis

skill-card.md:39

Medium External URL

http://192.168.1.234:9601/smyx-open-api

skills/smyx_common/scripts/config-dev.yaml:2

Medium External URL

http://192.168.1.234:4100

skills/smyx_common/scripts/config-dev.yaml:3

Medium External URL

http://192.168.1.234:7070/jeecg-boot-xzgz

skills/smyx_common/scripts/config-dev.yaml:4

Medium External URL

https://livemonitortest.lifeemergence.com/smyx-open-api

skills/smyx_common/scripts/config-test.yaml:2

Medium External URL

http://livemonitortest.lifeemergence.com

skills/smyx_common/scripts/config-test.yaml:3

Medium External URL

https://healthtest.lifeemergence.com/jeecg-boot-xzgz

skills/smyx_common/scripts/config-test.yaml:4

Medium External URL

https://lifeemergence.com/jeecg-boot-xzgz

skills/smyx_common/scripts/config.yaml:4

Medium External URL

https://open.lifeemergence.com/smyx-open-api

skills/smyx_common/scripts/config.yaml:5

Medium External URL

http://livemonitor.lifeemergence.com

skills/smyx_common/scripts/config.yaml:6

Dependencies and supply chain

Package	Version	Source	Known vuln	Notes
requests	`>=2.28.0`	pip	No	版本要求宽松
sqlalchemy	`未声明`	import	No	依赖未在 requirements 中声明
pydash	`未声明`	import	No	try/except 兼容处理
pyyaml	`未声明`	import	No	用于配置加载

File composition

31 files · 2812 lines

Python 18 files · 2490 linesMarkdown 4 files · 282 linesYAML 6 files · 29 linesText 2 files · 6 linesJSON 1 files · 5 lines

Files of concern · 5

skills/smyx_common/scripts/util.py Python · 718 lines

未声明的敏感文件读取 · 工作区路径检测算法

skills/smyx_common/scripts/config.py Python · 399 lines

未声明的环境变量读取

skills/smyx_common/scripts/dao.py Python · 499 lines

未声明的本地数据库操作

SKILL.md Markdown · 183 lines

https://lifeemergence.com/sample.html

skill-card.md Markdown · 59 lines

https://clawhub.ai/user/smyx-sunjinhui · https://clawhub.ai/smyx-sunjinhui/skills/smyx-psychology-analysis

Other files · psychology_analysis.py · skill.py · smyx_analysis.py · api_service.py · skill.py · api_service.py +1

31 files · 112.0 KB · 2812 lines

Python 18f · 2490LMarkdown 4f · 282LYAML 6f · 29LText 2f · 6LJSON 1f · 5L

├─ ▾ 📁 references

│ └─ 📝 api_doc.md Markdown 21L · 643 B

├─ ▾ 📁 scripts

│ ├─ 🐍 __init__.py Python 1L · 38 B

│ ├─ 🐍 config.py Python 24L · 651 B

│ ├─ 📋 config.yaml YAML 1L · 2 B

│ ├─ 🐍 psychology_analysis.py Python 229L · 8.1 KB

│ └─ 🐍 skill.py Python 23L · 567 B

├─ ▾ 📁 skills

│ ├─ ▾ 📁 smyx_analysis

│ │ ├─ ▾ 📁 references

│ │ │ └─ 📝 api_doc.md Markdown 19L · 427 B

│ │ ├─ ▾ 📁 scripts

│ │ │ ├─ 🐍 __init__.py Python 0 B

│ │ │ ├─ 🐍 api_service.py Python 40L · 1.5 KB

│ │ │ ├─ 🐍 config.py Python 39L · 1003 B

│ │ │ ├─ 📋 config.yaml YAML 1L · 3 B

│ │ │ ├─ 🐍 skill.py Python 175L · 6.4 KB

│ │ │ └─ 🐍 smyx_analysis.py Python 115L · 3.7 KB

│ │ ├─ 🐍 __init__.py Python 0 B

│ │ └─ 📄 requirements.txt Text 3L · 45 B

│ └─ ▾ 📁 smyx_common

│ ├─ ▾ 📁 scripts

│ │ ├─ 🐍 __init__.py Python 9L · 177 B

│ │ ├─ 🐍 api_service.py Python 101L · 2.6 KB

│ │ ├─ 🐍 base.py Python 33L · 469 B

│ │ ├─ 📋 config-dev.yaml YAML 6L · 214 B

│ │ ├─ 📋 config-prod.yaml YAML 0 B

│ │ ├─ 📋 config-test.yaml YAML 6L · 256 B

│ │ ├─ 🐍 config.py Python 399L · 23.8 KB

│ │ ├─ 📋 config.yaml YAML 15L · 473 B

│ │ ├─ 🐍 dao.py Python 499L · 17.8 KB

│ │ ├─ 🐍 skill.py Python 85L · 2.4 KB

│ │ └─ 🐍 util.py Python 718L · 28.1 KB

│ ├─ 🐍 __init__.py Python 0 B

│ └─ 📄 requirements.txt Text 3L · 47 B

├─ 📝 SKILL.md Markdown 183L · 10.3 KB

├─ 📋 _meta.json JSON 5L · 144 B

└─ 📝 skill-card.md Markdown 59L · 2.1 KB

Security positives

核心功能为合法的心理健康视频分析，无 RCE 或反向 shell

网络请求仅用于调用云端 API，无外部 IP 直连或 C2 通信

无 base64/bash 管道、裸 IP 请求等混淆技术

依赖版本有声明（requests>=2.28.0）

未访问 ~/.ssh、~/.aws、.env 等高风险敏感路径