bpmn

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow ingests the user-supplied .bpmn file contents (including any outsider-authored free-text like task names/annotations/conditionExpression bodies) via readFileSync(path, 'utf-8') → summarizeText()/lintModel()/validateModel() which parse and then convert that text into LLM-readable strings (e.g., summarizeText uses label() and prints names/conditions).