firecrawl

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md clearly instructs the agent to fetch and ingest public web content (e.g., "firecrawl search --scrape", "firecrawl scrape """, "firecrawl crawl", "firecrawl browser", and "firecrawl agent") which writes untrusted third‑party pages into .firecrawl/ files that the agent is expected to read and act on, creating exposure to indirect prompt injection.