firecrawl-agent

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the firecrawl CLI tool from the NPM registry via npx. This is a standard distribution method for the tool provided by the well-known Firecrawl service.
  • [COMMAND_EXECUTION]: Uses shell commands to execute the firecrawl agent, enabling web navigation and data extraction into local files. This is consistent with the skill's documented functionality.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes untrusted content from external websites. 1. Ingestion points: Website content from URLs provided in the --urls argument or discovered during autonomous navigation. 2. Boundary markers: None explicitly defined in the execution instructions. 3. Capability inventory: File system write access via the -o output flag in Bash tool execution. 4. Sanitization: No explicit sanitization or validation of the fetched web content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 06:16 AM