chrome-browser

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and execution instructions explicitly show navigating to arbitrary URLs and extracting/reading page content (e.g., devtools__navigate_page, devtools__get_network_request, mcp__claude-in-chrome__navigate, mcp__claude-in-chrome__read_page / __get_page_text), meaning the agent ingests untrusted public web/user-generated content which can influence subsequent clicks, fills, script execution, and tool actions.