bmad-help

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly instructs fetching and using module documentation located at URLs or remote sources ("Rows with _meta...carry a URL or path...Fetch and use these" and "retrieve all meta rows remote sources"), which means it will ingest third-party (potentially untrusted) content and use it to influence recommendations and next actions.