firecrawl-knowledge-base
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data by scraping web content from URLs or topics provided by the user. While this introduces a potential surface for indirect prompt injection, the skill's functionality is focused on content organization and file storage, and it does not expose dangerous capabilities to the processed data.
- Ingestion points: Web content retrieved via Firecrawl map/scrape operations.
- Boundary markers: Not explicitly defined in the prompt instructions.
- Capability inventory: Writing markdown and JSON files to the local
.firecrawl/directory. - Sanitization: Content is converted to markdown format; no specific script-level sanitization logic is present in the markdown instructions.
- [DATA_EXFILTRATION]: The skill requires a
FIRECRAWL_API_KEYfor authentication with the Firecrawl service. This is handled as a required input parameter, which is the recommended approach for managing secrets in agent skills. The network activity is restricted to communicating with the Firecrawl API to perform the requested scraping and mapping tasks.
Audit Metadata