bmad-editorial-review

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

• Third-party content exposure detected (high risk: 0.75). Yes—when the user provides “content” as a file path, the required workflow reads that file’s text at runtime (via scripts/word_metrics.py and then uses the document content for the review), so any outsider-authored document text the user points to can be ingested into the LLM context.