firecrawl-scrape

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the tool to "Scrape one or more URLs" (including JS-rendered pages) and offers a "--query 'Ask a question about the page'" option, meaning it fetches and interprets arbitrary public webpage content (untrusted third-party sources) that can affect outputs and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). This skill fetches arbitrary external URLs at runtime (e.g., "https://example.com/pricing") and injects the scraped page content into the agent/LLM context (via scrape and --query), so remote content can directly influence prompts and pose a prompt-injection/execution risk.