firecrawl

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly directs the agent to fetch and scrape arbitrary public web pages (e.g., "firecrawl scrape https://example.com", "firecrawl search ... --scrape") and to read and act on those scraped outputs, so the agent will ingest untrusted third‑party web content that could contain instructions affecting subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly runs firecrawl commands like "firecrawl scrape https://" at runtime to fetch arbitrary external https://... webpages and then injects that fetched content into the model context, meaning those runtime-fetched URLs can directly control agent prompts.