bmad-os-editorial-review-translation

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly requires ingesting "content" (translated file(s) or PR diff) as input — i.e., user-contributed, potentially public translation PRs — which the agent must read and use to make decisions (INJECTION/DRIFT/ORPHAN/OMISSION), exposing it to untrusted third-party content that could contain indirect prompt-injection.