accessibility-audit

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

• Third-party content exposure detected (high risk: 0.90). The skill's required inputs ask for "The site or product under audit" and the workflow explicitly instructs "Run automated scans across the priority pages" and to report "Critical findings ... with specific URLs" (SKILL.md and references/audit-report-template.md), which shows the agent will fetch and analyze open/public third-party web pages that can influence its actions.