mcp-firecrawl

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

• Third-party content exposure detected (high risk: 0.90). This skill directly instructs the agent to fetch and scrape arbitrary public web pages and search results (e.g., the firecrawl_scrape and firecrawl_search tools in SKILL.md and references/tools.md) so untrusted, user-generated web content would be read and used to drive extraction and LLM-based actions, enabling indirect prompt injection.