firecrawl-scraper

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to scrape websites and parse PDFs, creating an attack surface where malicious instructions in the external content could influence the AI agent.
  • Ingestion points: Web pages and PDF content retrieved via the Firecrawl API.
  • Capability inventory: Deep web scraping, crawling, and PDF parsing.
  • Boundary markers: The documentation does not specify the use of delimiters to isolate scraped content.
  • Sanitization: No data validation or sanitization processes are mentioned.
  • [EXTERNAL_DOWNLOADS]: The skill implementation is downloaded from an external GitHub repository (BenedictKing/firecrawl-scraper) during the installation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:33 PM