firecrawl-agent
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
firecrawlandnpx firecrawlCLI tools to perform its primary function of navigating websites and extracting structured data. - [EXTERNAL_DOWNLOADS]: The skill references the
firecrawlpackage vianpx, which involves downloading the tool from the official npm registry, a well-known technology service. - [PROMPT_INJECTION]: The skill processes untrusted data from external websites, creating an indirect prompt injection surface common to AI-based scrapers.
- Ingestion points: Web content is ingested from external URLs provided to the agent as described in
SKILL.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are specified in the skill's command templates.
- Capability inventory: The skill is authorized to run
firecrawlcommands and write extracted data to the local.firecrawl/directory. - Sanitization: No explicit sanitization or validation of the retrieved web content is defined within the skill's instructions.
Audit Metadata