soia-pkm-library-weread-sync
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the installation of the official Tencent/WeChatReading skill via the command npx skills add Tencent/WeChatReading -g -y as documented in the dependency section.
- [EXTERNAL_DOWNLOADS]: The Python scripts sync_weread_to_library.py, sync_weread_highlights.py, and enrich_book_details.py communicate with the official WeChat Reading API gateway at https://i.weread.qq.com/api/agent/gateway to retrieve user content.
- [DATA_EXFILTRATION]: The skill manages a WEREAD_API_KEY. It follows security best practices by providing a dedicated configuration location (~/.config/soia-skills/) to store the key, ensuring it remains outside the Obsidian vault and version-controlled files.
- [PROMPT_INJECTION]: The skill ingests untrusted data from an external API and writes it to the local file system. \n
- Ingestion points: External data is retrieved from the WeChat Reading API in all three primary sync scripts. \n
- Boundary markers: The skill uses specific markdown headers (e.g., ## 📌 划线（来自微信读书 · 自动同步）) and provides a ### 用户笔记 section to separate machine-generated content from user content. \n
- Capability inventory: The skill uses urllib.request for networking and pathlib for file writing within the vault. \n
- Sanitization: Book titles are cleaned of illegal characters using a clean_title function in sync_weread_to_library.py.
Audit Metadata