firecrawl

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the firecrawl-cli package globally using npm or npx. These references point to the official npm registry and well-known Firecrawl service repositories.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute firecrawl commands for scraping, searching, and browser automation. It provides clear instructions on quoting URLs to prevent shell-based command injection.
  • [DATA_EXFILTRATION]: The skill's primary purpose is web scraping, which involves fetching data from external URLs. This is an intended functionality. The skill mitigates risks by advising that results be written to a dedicated .firecrawl/ directory that is added to .gitignore.
  • [PROMPT_INJECTION]: The skill includes a dedicated security file (rules/security.md) that warns the agent about indirect prompt injection risks from scraped content. It provides mitigation strategies such as incremental reading and avoiding the direct execution of instructions found within the fetched data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 02:06 PM
Security Audit — agent-trust-hub — firecrawl