firecrawl-agent

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the firecrawl and firecrawl-cli commands via the Bash tool to execute autonomous web extraction tasks and manage background jobs.
  • [EXTERNAL_DOWNLOADS]: The skill references npx firecrawl-cli for runtime execution. This package is an official resource provided by the skill's author, and its use represents standard functionality for the tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to autonomously navigate and extract data from external websites, which presents a surface for processing untrusted content.
  • Ingestion points: Content from external websites retrieved through user-provided URLs or autonomous navigation (SKILL.md).
  • Boundary markers: None explicitly defined in the CLI command wrappers.
  • Capability inventory: The skill utilizes command execution to interact with the Firecrawl API and filesystem for writing JSON results (SKILL.md).
  • Sanitization: Data extraction and safety filtering are handled by the Firecrawl service infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 12:31 AM
Security Audit — agent-trust-hub — firecrawl-agent