The Agent Skills Directory

[SAFE]: The skill uses a standard environment variable (DOUBAOYA_API_KEY) for authentication, and the documentation contains explicit instructions to prevent the key from being printed or exposed in logs.
[SAFE]: The Python script is zero-dependency, relying exclusively on standard library modules like urllib and json, which eliminates risks associated with malicious external packages.
[SAFE]: Network operations are limited to a single, legitimate service endpoint (doubaoya.com) consistent with the skill's stated purpose.
[DATA_EXPOSURE]: The skill processes external content (titles and metadata from Xiaohongshu) which is then summarized by the agent. While this creates a surface for indirect prompt injection, the risk is minimal as the script outputs structured JSON and the agent's task is limited to creative refinement.

xiaohongshu-cover