The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides Python templates that use the subprocess module to execute curl commands. This is used specifically to communicate with the official WeChat Reading API gateway (https://i.weread.qq.com/api/agent/gateway).
[DATA_EXFILTRATION]: The skill accesses sensitive user reading data, including bookshelves, notebooks, and reading progress. However, this data is transmitted only to the official service provider's API endpoint required for the skill to function.
[EXTERNAL_DOWNLOADS]: The documentation references installation via npx skills add, which is the standard package management procedure for the target agent platform.
[PROMPT_INJECTION]: As an indirect risk, the skill processes external data such as book reviews and user notes which could theoretically contain malicious instructions. The skill handles this by focusing on structural analysis and specific workflows rather than blindly executing contents of the data.

huashu-weread-advisor