customer-discovery

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

• Third-party content exposure detected (high risk: 0.85). Yes—this skill’s required workflow performs runtime web fetching/scraping of outsider-authored HTML (e.g., Wayback Machine snapshots and company website pages) and then extracts text fields (alt/title/aria-label and headings) from that fetched content into the tool’s outputs that are typically fed back into the agent/LLM context for report generation.