broken-link-scan

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

• Third-party content exposure detected (high risk: 0.85). At runtime, the skill navigates to an operator-supplied URL and uses mcp__playwright__browser_evaluate to extract readable link text/URLs from that fetched page (public web content authored by outsiders), which is then included in the LLM’s context via the generated broken-link report.