jtbd

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

• Third-party content exposure detected (high risk: 0.70). The skill's required "Review-Mining Intake" workflow (SKILL.md) and the review-mining script (scripts/mine_reviews.py) explicitly ingest and analyze user-provided review exports—with taxonomy docs naming public sources like G2, App Store, and Google Maps—so it clearly reads untrusted, user-generated third-party content and uses those findings to drive interview flow, outputs, and downstream tool decisions.