customer-journey-map

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

• Third-party content exposure detected (high risk: 0.90). The skill's Context explicitly instructs the agent to "read" user-provided files and "use web search to understand the product if a URL is provided," which requires fetching and interpreting untrusted third-party content (public URLs and user-uploaded transcripts) as part of its workflow.