firecrawl-build-scrape
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references documentation and guidance from
docs.firecrawl.devandfirecrawl.dev. These are official domains for the Firecrawl scraping service. - [PROMPT_INJECTION]: Ingests untrusted content from external URLs, presenting a surface for indirect prompt injection attacks. 1. Ingestion points: Content is retrieved from user-provided URLs via the
/scrapeendpoint. 2. Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the scraped content. 3. Capability inventory: The skill is used to provide data for downstream LLM retrieval, summarization, and monitoring. 4. Sanitization: No specific sanitization or filtering of the scraped content is mentioned in the implementation notes.
Audit Metadata