linkedin-content-ideation

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

• Third-party content exposure detected (high risk: 0.75). The workflow’s “Mine Sources” step explicitly includes “Industry news,” “Search and hashtag conversations,” and “Comments and replies,” which at runtime would typically require fetching/ingesting outsider-authored free text from public web/social channels into the agent’s LLM context (indirect prompt injection risk).