Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/firecrawl-hello-world/Gen Agent Trust Hub

firecrawl-hello-world

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions and code for scraping and crawling external websites, which introduces a surface for indirect prompt injection from untrusted web content.
  • Ingestion points: External data enters the agent context via firecrawl.scrapeUrl, firecrawl.crawlUrl, and firecrawl.mapUrl calls documented in SKILL.md.
  • Boundary markers: The provided code snippets do not include explicit delimiters or instructions for the agent to ignore embedded commands within the scraped text.
  • Capability inventory: The skill environment permits Read, Write, and Edit tools, which could potentially be targeted if the agent obeys instructions found on a malicious webpage.
  • Sanitization: The minimal examples do not demonstrate sanitization or validation of the scraped markdown/JSON data before processing.
  • [EXTERNAL_DOWNLOADS]: The skill references and recommends the installation of official Firecrawl client libraries from public registries.
  • Evidence: The documentation suggests installing the @mendable/firecrawl-js package via npm install.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 01:34 AM