Security audit
Security checks across malware telemetry and agentic risk
The skill is not clearly malicious, but its main finance workflow can produce authoritative-looking reports from hardcoded articles and random sentiment labels.
Review this skill carefully before installing or using it. Treat the main.py output as prototype/demo output unless the mock news and random sentiment paths are replaced with real fetching and validated analysis. Do not rely on generated briefings for trading decisions, and only run provider-backed analysis after choosing which LLM service may receive your news text and API credentials.
### Q: 本地模型怎么安装？ ```bash # 1. 安装 Ollama curl -fsSL https://ollama.com/install.sh | sh # 2. 下载模型 ollama pull llama3.1
## 基础依赖（必需） ```txt requests>=2.31.0 beautifulsoup4>=4.12.0 lxml>=4.9.0 jinja2>=3.1.0
## 基础依赖（必需） ```txt requests>=2.31.0 beautifulsoup4>=4.12.0 lxml>=4.9.0 jinja2>=3.1.0 pyyaml>=6.0
```txt requests>=2.31.0 beautifulsoup4>=4.12.0 lxml>=4.9.0 jinja2>=3.1.0 pyyaml>=6.0 ```
requests>=2.31.0 beautifulsoup4>=4.12.0 lxml>=4.9.0 jinja2>=3.1.0 pyyaml>=6.0 ```
beautifulsoup4>=4.12.0 lxml>=4.9.0 jinja2>=3.1.0 pyyaml>=6.0 ``` ## LLM API 依赖（可选，根据使用模型安装）
### OpenAI (GPT 系列) ```txt openai>=1.0.0 ``` ### Anthropic (Claude 系列)
### Anthropic (Claude 系列) ```txt anthropic>=0.18.0 ``` ### 阿里通义千问
### 阿里通义千问 ```txt dashscope>=1.14.0 ``` ### 百度文心一言
### 百度文心一言 ```txt qianfan>=0.3.0 ``` ### 智谱 AI (GLM 系列)
### 智谱 AI (GLM 系列) ```txt zhipuai>=2.0.0 ``` ### Ollama (本地模型)
## 完整安装（所有模型支持） ```txt requests>=2.31.0 beautifulsoup4>=4.12.0 lxml>=4.9.0 jinja2>=3.1.0
## 完整安装（所有模型支持） ```txt requests>=2.31.0 beautifulsoup4>=4.12.0 lxml>=4.9.0 jinja2>=3.1.0 pyyaml>=6.0
```txt requests>=2.31.0 beautifulsoup4>=4.12.0 lxml>=4.9.0 jinja2>=3.1.0 pyyaml>=6.0 openai>=1.0.0
requests>=2.31.0 beautifulsoup4>=4.12.0 lxml>=4.9.0 jinja2>=3.1.0 pyyaml>=6.0 openai>=1.0.0 anthropic>=0.18.0
66/66 vendors flagged this skill as clean.
No suspicious patterns detected.
