firecrawl-scrape

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly scrapes arbitrary public URLs (see SKILL.md "Scrape one or more URLs" and the example commands) and returns/queries the page content for the agent to read and act on, so untrusted third-party webpages could inject instructions that influence behavior.

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 web pages at runtime (e.g., https://example.com) and injects their scraped content into the model context for queries/responses, so remote content can directly control prompts or instructions.