content-fission

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow ingests the “user-provided article” text (which may be authored by someone other than the operating user) into the assistant for outline extraction and summarization, creating an outsider-authored free-text injection surface via the user’s pasted/linked article content.