oz-child-agent-orchestration

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow includes polling and reading the agent messaging inbox via "$OZ_CLI" run message list and "$OZ_CLI" run message read $MESSAGE_ID, which will ingest free-text message bodies authored by the (potentially user-controlled) outsider submitter to that queue/inbox.