firecrawl-deploy-integration

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill references and downloads the official Firecrawl SDK (@mendable/firecrawl-js) and uses verified Docker images for Firecrawl and Redis services from their official repositories.
  • [PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by configuring endpoints that process untrusted data retrieved from the web via the Firecrawl API.
  • Ingestion points: External data is ingested through the req.json() calls in the scraping and webhook handlers within api/scrape.ts and api/webhooks/firecrawl.ts.
  • Boundary markers: The provided code examples do not include delimiters or specific instructions to the agent to disregard potential commands embedded within the scraped content.
  • Capability inventory: The agent environment has access to file system modification tools and shell command execution through various platform CLIs (vercel, fly, gcloud).
  • Sanitization: No logic is provided in the templates to validate, filter, or sanitize the content returned by the scraping service before it is presented to or processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 05:37 PM