agent-apprenticeship-ecosystem

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context via the “Learning from Ecosystem” workflow: apprentice ecosystem pull / apprentice learn create / apprentice run --experience-pack can ingest community experience bundles (from ecosystem/contributions / configured repo) whose task text and execution traces are authored by others.