grill-me

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests user-provided plan/design text via the required runtime path scripts/decision_tree_extractor.py (regex scan of the provided markdown file), then scripts/question_generator.py and scripts/grill_session_tracker.py use that extracted free text to generate questions.