lifecycle-sequence-generator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly checks for app-store review data at neobank-skills/app-store-intelligence/output/{slug}-reviews.json and, per SKILL.md Step 1 and the Day 3 workflow, pulls real user complaint language from those app-store reviews (public, user-generated content) to shape generated messages, meaning untrusted third-party text is ingested and directly influences generation decisions.