firecrawl-policy-guardrails

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to crawl and ingest arbitrary web pages (e.g., the example using firecrawl.crawlUrl(url) and the validateScrapedContent/filter steps), which pulls untrusted public third‑party content that the agent reads and uses to decide follow-up actions.