firecrawl-website-design-clone
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
firecrawlCLI to scrape website data, which is standard functionality for this vendor-provided skill. - [PROMPT_INJECTION]: The skill processes untrusted content from external websites, creating a surface for indirect prompt injection.
- Ingestion points: Website metadata, branding data, and markdown content retrieved via the Firecrawl CLI (SKILL.md).
- Boundary markers: Absent. The instructions do not specify that the agent should ignore instructions or commands embedded within the scraped website data during synthesis.
- Capability inventory: The agent has permissions to write files (creating DESIGN.md and local storage in .firecrawl/) and execute shell commands (via the Firecrawl CLI).
- Sanitization: Absent. The skill synthesizes data directly from the scrape output into the final markdown deliverable without explicit filtering or validation steps.
Audit Metadata