app-store-optimization

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via the Review Sentiment Analysis workflow: the skill’s review_analyzer.py expects reviews[].text (review body text authored by app users/outsiders) and the agent typically passes that text into the LLM to summarize themes/complaints.