firecrawl-monitor

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Bash(firecrawl *) and Bash(npx firecrawl *) to interface with the Firecrawl service. These tools are used to create, list, and manage web monitors, including writing configuration to temporary JSON files for complex extraction tasks.
  • [DATA_EXFILTRATION]: The skill includes functionality to send alerts to external --webhook-url and --email addresses. This is a core feature of the monitoring service intended for notification delivery to user-specified endpoints.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes content from external websites.
  • Ingestion points: The skill ingests data from external URLs (--page, --crawl-url) and search engine results (--queries) during the monitoring process.
  • Boundary markers: No specific boundary markers or instructions to treat monitoring diffs as untrusted are explicitly defined in the skill instructions, although the service uses an internal AI judge.
  • Capability inventory: The skill can execute shell commands via Bash and perform network operations through the firecrawl CLI.
  • Sanitization: The skill relies on a server-side 'AI change judge' to filter out formatting noise and provides structured JSON diffs, which helps isolate relevant content changes from raw page data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 01:04 AM
Security Audit — agent-trust-hub — firecrawl-monitor