political-struggle-history

解说中国和西欧历史上的政治斗争事件。涵盖中国从先秦到清末、西欧从古罗马到19世纪的宫廷政变、党争、权臣专权、宗教冲突、革命等重大政治斗争，并支持中西对比分析。当用户询问历史政治斗争、宫廷政变、权力斗争时自动触发。

This skill looks like a legitimate historical explainer, but it has a few practical and privacy-related mismatches you should consider before installing or enabling it: (1) SKILL.md and scripts require a TAVILY_API_KEY (an external API key) but the skill metadata does not declare this — providing that key will let the script send search queries and results (including the user's query text) to Tavily; (2) the bundled search script depends on the third‑party Python package 'tavily' (tavily-python). The package isn't declared in an install spec, so running the skill may fail or cause the agent to pip install packages at runtime; verify the package's provenance before allowing installs; (3) SKILL.md contains an absolute developer path (/Users/hazelnut/...) as a fallback — harmless by itself but a sign the author used a local dev environment and the fallback could cause the agent to attempt reading unexpected local paths in some setups; (4) the skill runs a Python script via Bash when --search is used, so only use the search feature if you trust sending queries to an external service and are comfortable the environment has the proper dependency. Recommendations: (A) if you will use the skill without networked search, disable or ignore the --search option; (B) if you want the search feature, obtain and review the tavily-python client and Tavily's privacy policy, and provide a dedicated API key with minimal scope (or test in an isolated environment); (C) ask the publisher for an explicit dependency/installation spec and a reason for the absolute-path fallback or for them to remove it; (D) if unsure, run the skill in a sandboxed/isolated environment or decline to install until the env var and dependency are declared in the registry metadata.

Type: OpenClaw Skill Name: political-struggle Version: 1.0.0 The skill is classified as suspicious due to the combination of allowing the `Bash` tool and a critical prompt injection vulnerability in `SKILL.md`. The instruction '如果脚本执行报错，使用 Bash 工具中的 `allowed-tools` 权限直接运行并排查问题' (If the script execution errors, use the `Bash` tool's `allowed-tools` permission to directly run and troubleshoot the problem) explicitly directs the AI agent to use `Bash` for debugging in case of script failure. This creates a significant attack surface where a malicious user could intentionally cause the `scripts/search_views.py` script to fail and then, through prompt injection, guide the agent to execute arbitrary shell commands under the guise of 'troubleshooting'. While the `search_views.py` script itself appears to perform legitimate web searches using the Tavily API (requiring `TAVILY_API_KEY`), the broad `Bash` permission and the debugging instruction introduce a high-risk vulnerability.