The Agent Skills Directory

[SAFE]: The skill serves a legitimate purpose for academic research and metadata management. Its operations are transparent and consistent with its described functionality.\n- [DATA_EXFILTRATION]: Network activity is restricted to 127.0.0.1:23119, the standard port for local Zotero integration. There is no evidence of data being sent to external or untrusted domains.\n- [COMMAND_EXECUTION]: The skill executes a local Python script to process and push data to Zotero. The script uses standard libraries for JSON processing and HTTP requests, with no dynamic code execution or obfuscation detected.\n- [PROMPT_INJECTION]: The instructions in SKILL.md are focused on functional usage and do not contain any patterns typical of prompt injection or attempts to bypass agent safety guidelines.

wos-export