PaperCash — 论文全流程辅助 Skill

论文全流程辅助: 8源检索、综述生成、查重预检、降AI率、参考文献格式化、Word导出

This skill appears to implement what it claims, but take these precautions before installing or giving it sensitive inputs: - It executes the included Python CLI: inspect scripts/papercash.py and the features/ modules yourself if possible. The skill will read files you point it at and send queries (and parts of your text) to external academic services during search and plagiarism checks. - Optional configuration asks for CNKI/WANFANG cookies and a Google Scholar proxy. Do not paste real account cookies or long-lived session tokens into config files unless you trust the author and understand the risk; prefer using only free public sources (Semantic Scholar, arXiv, CrossRef) if privacy matters. - The 'humanize' (降AI率) capability helps evade AI-detection and could facilitate academic misconduct; use responsibly and follow your institution's policies. - Review hooks/session_start.py (and any hook code) before installing — hooks can run at session start and increase the blast radius. - If you decide to use it, run it in an isolated environment (container or VM), avoid supplying sensitive documents to optional sources that require cookies, and monitor outbound network requests (or restrict networking) until you are comfortable with its behavior.

Type: OpenClaw Skill Name: papercash Version: 1.0.0 PaperCash is a comprehensive academic assistant tool designed for paper searching, literature review generation, and citation formatting. It integrates with eight academic data sources including Semantic Scholar, arXiv, and CrossRef. While the tool handles sensitive information such as session cookies for paywalled Chinese databases (CNKI and Wanfang) and performs network requests to various academic APIs, these behaviors are transparently documented and strictly necessary for its stated functionality. The code is well-structured, follows security best practices like input sanitization for filenames in `docx_export.py`, and lacks any evidence of data exfiltration, obfuscation, or malicious intent. The instructions in `SKILL.md` are appropriately aligned with the tool's purpose and do not contain prompt-injection attacks against the agent.