firecrawl-agent
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
firecrawlCLI tool to navigate websites and extract structured data as JSON. - [SAFE]: No malicious patterns, such as credential harvesting, obfuscation, or persistence mechanisms, were detected.
- [SAFE]: The processing of untrusted web content (Indirect Prompt Injection surface) is the core purpose of the tool and is deemed safe in this context. Ingestion points: external web data retrieved during navigation (SKILL.md). Boundary markers: none explicitly defined in the CLI prompts. Capability inventory: execution of the
firecrawlCLI and local file system writes (SKILL.md). Sanitization: employs JSON schema validation for structured outputs.
Audit Metadata