content-writer

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

• Third-party content exposure detected (medium risk: 0.30). The skill ingests competitor-provided “candidate URL/content” (including traffic/ranking history and competitor examples for refresh mode), and it explicitly treats pasted exports/URLs as untrusted input, so outsider-authored free text can be supplied via user-submitted content/URLs that the workflow then reads.