review

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly asks users to "Paste the text or provide a link/file path" for the draft, meaning the agent will ingest and interpret arbitrary user- or web-sourced content (untrusted third-party material) as part of its review workflow, which could enable indirect prompt injection.