firecrawl
Warn
Audited by Snyk on Mar 8, 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's SKILL.md explicitly directs the agent to run firecrawl search/scrape/map commands against arbitrary web URLs (e.g., "firecrawl scrape https://example.com", "firecrawl search 'your query'") and to read scraped output files, which ingests untrusted public web and user-generated content that can influence subsequent actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run the Firecrawl CLI to scrape arbitrary external pages at runtime (e.g., "firecrawl scrape https://example.com -o .firecrawl/example.md"), and those fetched pages are intended to be injected into the model context and thus can directly control agent prompts.
Audit Metadata