brand-illustrate

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

• Third-party content exposure detected (medium risk: 0.30). The runtime adapter scripts/illustrate.py ingests outsider-authored free text provided via the user questionnaire/answers.json (e.g., subject, style, variants, negatives) and embeds it into the generated prompt scaffold for backend execution and prompts.md output.