obsidian-literature-workflow

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs using $zotero-obsidian-bridge to pull Zotero-sourced papers and then scans/parses Papers/.md and Knowledge/.md (see SKILL.md steps 2–5 and the scripts build_literature_canvas.py / build_literature_graph.py), so untrusted third‑party content (Zotero/public papers) is ingested and directly influences note creation, graph building, and follow-up actions.