Paper Compare

Compare academic research papers side-by-side to identify similarities, differences, and research gaps. Use when user wants to compare 1-5 papers via DOIs, U...

This skill appears to be what it says: a paper-comparison helper that fetches metadata and (optionally) extracts text from PDFs. Before installing or invoking: 1) Verify the agent has only the network/tool permissions you expect (web_fetch/web_search and the pdf extraction tool). PDF extraction tools sometimes upload files to third-party services—confirm where PDFs are processed if you will send unpublished or sensitive documents. 2) If you plan heavy use, consider whether Semantic Scholar or other APIs require an API key or have rate limits; the SKILL.md references endpoints but does not declare keys. 3) Note the skill will access external URLs you provide (arXiv/IEEE/PubMed/etc.), so avoid giving confidential URLs you don't want fetched. 4) The skill depends on other agent tools (pdf skill, web_fetch); review those tools' behaviors/privileges because any risk from those tools affects this skill. Overall, nothing in this skill's instructions is disproportionate or unexplained, but runtime risk depends on the agent's tool permissions and how PDFs are processed.

Type: OpenClaw Skill Name: paper-compare Version: 1.2.1 The skill bundle is benign. The `SKILL.md` file provides clear, structured instructions for an AI agent to compare academic papers using legitimate external APIs (crossref.org, semanticscholar.org) and standard OpenClaw skills (web_fetch, web_search, pdf). There are no instructions for data exfiltration, malicious execution, system-level persistence, or prompt injection designed to subvert the agent's purpose. The 'persistence' mentioned refers to saving comparison history to an internal memory file (`memory/paper-compare-history.json`), which is a benign feature for remembering past interactions.