apple-app-store-reviewer

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text via review-input.json (user-supplied config) and then runs AI semantic evaluation cases/prompts (e.g., scripts/review_app.py + scripts/run_ai_safety_suite.py using assets/ai-safety-test-cases.json), meaning arbitrary text provided by the provider user can reach LLM prompting at runtime without selecting a specific trusted item first.