webperf

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md workflow step 3 instructs the agent to navigate to a target URL using mcp__chrome-devtools__navigate_page and run/evaluate scripts on that page, meaning it fetches and interprets untrusted public webpages (console results) which can materially influence subsequent analysis and recommendations.