The Agent Skills Directory

[SAFE]: The skill is a standard search integration for a legitimate academic data provider (Wanfang Data). All external communication is restricted to the official vendor domain api.wfdata.com.
[CREDENTIALS_SAFE]: The scripts properly handle authentication by retrieving the application key from the WFDATA_APP_KEY environment variable, avoiding hardcoded secrets and following secure configuration practices.
[COMMAND_EXECUTION]: The tools do not execute shell commands or spawn subprocesses. User-provided search queries are treated as data and transmitted within JSON payloads to the search API.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a data ingestion point for search results. While it lacks explicit boundary markers or sanitization for retrieved content, the risk is negligible as the skill has no dangerous capabilities (such as file writing or code execution) that could be triggered by poisoned data.
[DATA_EXFILTRATION]: Network activity is limited to the search service's official API. There are no patterns suggesting the exfiltration of local sensitive files or environment data.

wfdata-search