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 describes scraping arbitrary public URLs ("Scrape one or more URLs", quick start examples like firecrawl scrape "") and includes a --query mode to read/interpret page content, so the agent ingests untrusted third-party web content that could contain instructions influencing its actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches arbitrary user-supplied URLs at runtime (e.g., "https://example.com" / the "" parameter) and uses the scraped page content to drive --query/LLM prompts, so remote pages can directly control model input.