amazon-alexa-qa

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow reads Alexa/Rufus response text from the page DOM via scripts/extract-response.py (e.g., .rufus-status-sr-only and .rufus-papyrus-active-turn), which is outsider-authored free text generated by Amazon’s assistant rather than the operating user.