firecrawl
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and processes arbitrary public web content (e.g., SKILL.md/README and scripts like scripts/agent.py, scripts/scrape.py, scripts/search.py, scripts/extract.py) using the Firecrawl API to autonomously search, crawl, scrape, and extract data from third‑party websites/URLs, meaning untrusted user-generated pages can be read and can influence the agent's actions.
Audit Metadata