firecrawl
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites retrieved via the Firecrawl CLI or MCP server, which presents an attack surface for indirect prompt injection. The workflow does not include explicit boundary markers or instructions for the agent to ignore instructions embedded within the scraped content. Given the skill's capabilities—such as shell command execution and file writing—and the suggestion to pass results to downstream Python scripts, the impact of malicious content could be escalated. There are no defined sanitization or validation steps for the extracted data before it enters the agent's context or is processed by other tools.
Audit Metadata