firecrawl-build-scrape
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to fetch and process data from external web pages, which introduces a surface for indirect prompt injection.
- Ingestion points: The skill facilitates retrieving content such as markdown and HTML from any URL provided to the
/scrapeendpoint (referenced inSKILL.md). - Boundary markers: The instructions do not mandate the use of specific delimiters or headers to distinguish untrusted web content from the agent's core instructions.
- Capability inventory: The scraped data is intended for retrieval-augmented generation (RAG), summarization, and monitoring, where the agent will directly process the fetched text.
- Sanitization: No explicit guidance is provided regarding the sanitization or filtering of the external content before it is ingested into the agent's context.
- [EXTERNAL_DOWNLOADS]: The skill references documentation and integration guides hosted on Firecrawl's official domain.
- Evidence: Links to
docs.firecrawl.devfor various language implementations (Node, Python, Rust, etc.) are provided inSKILL.md.
Audit Metadata