skills/vm0-ai/vm0-skills/firecrawl/Gen Agent Trust Hub

firecrawl

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill interacts with the official Firecrawl API (api.firecrawl.dev), which is a well-known service for web scraping and crawling.
  • [SAFE]: Credentials such as FIRECRAWL_TOKEN are managed using environment variables and platform secrets, adhering to security best practices.
  • [COMMAND_EXECUTION]: The skill uses curl and jq for API interaction and data parsing, involving standard command-line execution and local file writes for temporary configurations.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to its core function of scraping external websites.
  • Ingestion points: Data enters the context from untrusted URLs via Firecrawl's scrape and crawl endpoints.
  • Boundary markers: No delimiters are currently specified to separate untrusted content from the agent's instructions.
  • Capability inventory: The skill uses curl for network access and can write files to the local system.
  • Sanitization: There is no explicit sanitization of the scraped data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 01:47 AM