firecrawl-scraper

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs network requests to api.firecrawl.dev to facilitate web scraping. This is the expected and documented behavior for the Firecrawl service wrapper.
  • [COMMAND_EXECUTION]: The skill runs a local Node.js helper script via the Bash tool to manage API interactions and JSON data processing.
  • [PROMPT_INJECTION]: The skill ingests data from external websites, creating an indirect prompt injection surface. 1. Ingestion points: Data is fetched from arbitrary URLs via scripts/firecrawl-api.cjs. 2. Boundary markers: Scraped content is encapsulated within JSON response structures. 3. Capability inventory: The skill uses local shell execution and HTTPS requests. 4. Sanitization: The skill returns raw content from the API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 12:14 AM
Security Audit — agent-trust-hub — firecrawl-scraper