seo-firecrawl

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is primarily designed to ingest and analyze data from external websites, creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through the firecrawl_crawl, firecrawl_scrape, and firecrawl_search tools, which fetch content from user-provided URLs.
  • Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for handling potentially malicious content embedded in the crawled pages.
  • Capability inventory: The skill uses the fetched content to perform SEO audits, technical analysis, and content inventory, potentially influencing subsequent agent decisions or subagent prompts.
  • Sanitization: The skill lacks explicit sanitization or filtering logic for the content retrieved from external sources.
  • [EXTERNAL_DOWNLOADS]: The skill references an external dependency on the Firecrawl MCP server and directs the user to an installation script.
  • Evidence: References ./extensions/firecrawl/install.sh for installation and requires a connection to the Firecrawl MCP server.
  • [COMMAND_EXECUTION]: The documentation includes instructions for running a local shell script to install the necessary components.
  • Evidence: Provides the command ./extensions/firecrawl/install.sh in the setup instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 08:46 AM
Security Audit — agent-trust-hub — seo-firecrawl