linkedin-ghostwriting

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

• Third-party content exposure detected (low risk: 0.10). In SKILL.md the workflow has the model “Read the whole signal feed” and “Read the history first” (ledger and “last several live posts”) before drafting, but the text does not specify any outsider-authored free-text ingestion path beyond user-provided voice cards/ledgers and the “signal feed” content itself (no queue/feed/email/comment/chat/inbox ingestion is described), so the runtime exposure is not clearly outsider-controlled free text.