clone-website

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly scrapes arbitrary user-supplied URLs via the firecrawl-mcp___firecrawl_scrape (with fallback firecrawl_crawl), ingests untrusted public webpage HTML/markdown that the agent must analyze in the mandatory Phase 2 analysis, and then uses that content to drive code generation and asset downloads in Phase 3, creating a clear vector for indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill issues a runtime scrape via firecrawl-mcp___firecrawl_scrape with url: [TARGET_URL], pulling arbitrary external page content (markdown/html) into the agent's analysis and code-generation flow—i.e., external content fetched at runtime is injected into prompts and directly controls the agent's output.