content-creator

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime path uses get_user/list_users/list_posts from the JSONPlaceholder service to obtain author profiles and other posts; these are outsider-authored free-form text (e.g., post bodies/names) that the agent will ingest into the LLM context for drafting/output.