firecrawl-scraper

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing necessary software development kits and references external source code repositories.
  • Documentation includes commands to install the firecrawl-py package via pip and the @mendable/firecrawl-js or firecrawl packages via npm/pnpm.
  • The skill references a third-party GitHub repository G4brym/workers-firecrawl as an alternative implementation for Cloudflare Workers.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to scrape and crawl content from arbitrary external websites, which creates a potential surface for indirect prompt injection if the fetched content contains malicious instructions.
  • Ingestion points: Data enters the agent's context through the scrape_url, crawl_url, and extract functionality described in the skill.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded in the scraped data.
  • Capability inventory: The documentation provides examples of the agent performing file-write operations (with open(..., "w")) using data retrieved from external sources.
  • Sanitization: The skill lacks instructions or code examples for sanitizing, validating, or filtering content retrieved from the web before it is processed or stored.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 12:32 PM