firecrawl

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes arbitrary public web content (see SKILL.md "Get Page as Markdown", "Web Search", "Crawl Documentation" and the fc.py functions cmd_markdown, cmd_search, cmd_crawl) — it ingests untrusted third‑party pages/URLs and reads/parses their content as part of its workflow, which could allow indirect prompt injection to influence actions.