Literature Reviewer Skill

This skill is internally consistent for automated literature searching and synthesis, but it intentionally uses browser automation and may reuse browser cookies/login state and persistent Playwright data. Before installing or running it: (1) Prefer running inside the provided Docker container or another isolated sandbox to avoid exposing your host browser profile and credentials. (2) Inspect the scripts (scripts/*.py) and the SKILL.md to confirm there are no unexpected external endpoints; verify network domains are limited to the declared academic sites. (3) Avoid mounting host browser profiles or sharing real authentication cookies into the skill; remove or restrict the browser-data volume if you want stronger isolation. (4) Be aware scrapers can violate database terms of service and may trigger CAPTCHAs — review institutional access/legal constraints. (5) If you need paywalled content, prefer using institutionally-approved APIs or a dedicated account created for this tool rather than exposing your primary browser session. If you want, I can list the exact lines in the code that read/write session files, perform downloads, or reference browser-data so you can review them before running.

These patterns were detected by automated regex scanning. They may be normal for skills that integrate with external APIs. Check the VirusTotal and OpenClaw results above for context-aware analysis.