Zotero

Manage Zotero reference libraries via the Web API. Search, list, add items by DOI/ISBN/PMID (with duplicate detection), delete/trash items, update metadata and tags, export in BibTeX/RIS/CSL-JSON, batch-add from files, check PDF attachments, cross-reference citations, find missing DOIs via CrossRef, and fetch open-access PDFs. Supports --json output for scripting. Use when the user asks about academic references, citation management, literature libraries, PDFs for papers, bibliography export, or Zotero specifically.

This skill appears coherent and limited to managing Zotero libraries. Consider the following before installing: 1) Only provide a Zotero API key with the minimum necessary permissions (create a write-restricted key if you only need read access). 2) The script will send your API key over the network to api.zotero.org (this is required for the functionality) — only use it if you trust the skill source. 3) The fetch-pdfs commands may download PDFs and optionally upload them to your Zotero storage; review and use --dry-run and --download-dir first. 4) Although the code is small and uses the Python standard library, you should review scripts/zotero.py if you want to be certain there is no unwanted behavior (the package source/homepage is unknown). 5) Because the skill is not always-enabled, it won't run automatically — you must invoke it (or grant the agent permission to invoke it).

Type: OpenClaw Skill Name: zotero Version: 1.0.0 The OpenClaw Zotero skill is benign. The Python script uses only standard library modules, significantly reducing supply chain risk. All network interactions are with legitimate Zotero, CrossRef, Unpaywall, Semantic Scholar, and DOI resolution APIs, aligning perfectly with the stated purpose of managing academic references. The skill implements robust input validation for DOIs, ISBNs, and item keys, and includes safe defaults like 'trash-by-default' for deletions and 'dry-run' for bulk operations (`find-dois`, `fetch-pdfs`). There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts in any of the analyzed files.