ai-search-browser-use

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

• Third-party content exposure detected (high risk: 0.90). The skill drives a real browser via Chrome CDP to open public endpoints (https://gemini.google.com and https://chat.qwen.ai) and its ai_query.py/extract_js reads the pages' response text ('.markdown' innerText) to synthesize answers, so it consumes untrusted third‑party web content that could carry indirect prompt injection.