firecrawl-scraper

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses official Firecrawl API endpoints (api.firecrawl.dev) and official SDKs for web data extraction.
  • [SAFE]: Credential management instructions follow industry best practices by recommending environment variables and .env files instead of hardcoding API keys.
  • [SAFE]: External dependencies are limited to well-known, versioned packages from official registries like PyPI and NPM.
  • [SAFE]: File system access in the provided templates is restricted to local directories for caching and output storage, which is consistent with the skill's documented behavior.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted web content, which presents a surface for indirect prompt injection where malicious instructions on a website could attempt to influence the agent.
  • Ingestion points: Data retrieved from external URLs via the scrape and crawl endpoints.
  • Boundary markers: None; the skill retrieves and returns content without wrapping it in specific security delimiters.
  • Capability inventory: Network access to the Firecrawl API and file-writing capabilities in the crawl template script.
  • Sanitization: None; the skill retrieves content as markdown or JSON without additional filtering of the retrieved data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 09:40 AM
Security Audit — agent-trust-hub — firecrawl-scraper