full-engagement-pipeline

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md’s required workflow routes “Folder dump / do accounting / little client context” through shared/smart-intake.md, which (by its described “Read files → Hypothesis Card → extract” behavior) will ingest the user-provided dumped files’ text into the LLM context, and those files are outsider-authored relative to the operating user.