firecrawl-agent
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto fetch and execute thefirecrawlpackage from the official npm registry. - [COMMAND_EXECUTION]: It utilizes the
firecrawl agentcommand-line tool to automate web scraping and structured data extraction tasks. - [PROMPT_INJECTION]: The skill processes untrusted website content, which creates an attack surface for indirect prompt injection. 1. Ingestion points: Data is retrieved from external URLs via the
firecrawl agentcommand. 2. Boundary markers: No delimiters or isolation instructions are present to separate website content from the agent's instructions. 3. Capability inventory: The skill can execute shell commands and write extracted data to the local filesystem. 4. Sanitization: No sanitization or validation of the retrieved website content is described in the skill.
Audit Metadata