clone-website

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly directs the agent to navigate to the user-provided target URL via Chrome MCP and to extract/download live site content (text, images, videos, computed styles, behaviors) as the primary input for spec files and builder prompts (see "Phase 1: Reconnaissance" and repeated Chrome MCP/download instructions in SKILL.md), which exposes it to arbitrary untrusted third‑party web content that can influence downstream tool actions.