The Agent Skills Directory

[COMMAND_EXECUTION]: The script weibo_hot.sh utilizes standard system utilities curl and jq to perform network requests and parse JSON data. This is consistent with the skill's primary purpose.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to https://v2.xxapi.cn/api/weibohot to retrieve real-time data. While this is a third-party domain, its use is documented and directly related to the skill's functionality.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests and processes untrusted data (Weibo hot search titles) from an external API.
Ingestion points: Data enters the agent context via the API response fetched in weibo_hot.sh.
Boundary markers: No explicit instructions are provided to the agent to treat the fetched content as data rather than instructions.
Capability inventory: The skill uses curl and jq to fetch data; the agent may then use this data in subsequent reasoning steps.
Sanitization: The script performs basic JSON parsing but does not sanitize or escape the content of the title field before outputting it.

weibo-hot