read-source

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly supports fetching and reading arbitrary public URLs (see "Read from URLs" and the Quick Reference example witan read https://example.com/report.pdf in SKILL.md), so untrusted third‑party web content is ingested and can influence downstream parsing and spreadsheet actions.