alterlab-pyzotero

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and reads arbitrary library items, attachments, HTML snapshots, and full-text content via the Zotero Web API (see references/files-attachments.md and references/full-text.md where zot.dump, zot.file, zot.fulltext_item and collection downloads are used), which can include untrusted user-provided or public web content that the agent is expected to parse and that could materially influence subsequent actions.