firecrawl-knowledge-base

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and scrape public URLs and web pages (e.g., "turn URLs or topics into organized LLM-ready content" and "scrape pages into markdown"), which are untrusted third‑party sources the agent will read and ingest as part of its workflow.