firecrawl-build-scrape
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is composed entirely of markdown documentation and YAML configuration. It does not include any executable code, scripts, or automated commands.
- [SAFE]: All external links and repository references point to official Firecrawl domains and GitHub organizations, which are trusted sources for this vendor's tools.
- [PROMPT_INJECTION]: The skill outlines the implementation of web scraping, which creates a potential surface for indirect prompt injection. If an agent processes untrusted content from the web without proper isolation, it could be influenced by malicious instructions hidden on those pages.
- Ingestion points: Scraped content from external URLs (SKILL.md)
- Boundary markers: None specified in the implementation guidelines
- Capability inventory: Retrieval of page content, metadata, and structured data (SKILL.md)
- Sanitization: Not addressed in the current documentation.
Audit Metadata