firecrawl-search
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx firecrawl, which downloads the Firecrawl command-line tool from the npm registry. This is a legitimate resource from the skill author. - [COMMAND_EXECUTION]: The skill requires permission to execute the
firecrawlCLI andnpxcommands to perform web searches and data extraction. - [PROMPT_INJECTION]: The skill processes untrusted web data from search results and scraped pages, creating a surface for indirect prompt injection.
- Ingestion points: Web search results and full-page markdown content extracted from arbitrary URLs.
- Boundary markers: The skill instructions do not specify any delimiters or warnings to ignore instructions embedded in the scraped content.
- Capability inventory: The agent has the ability to execute
firecrawlandnpxcommands in the shell. - Sanitization: No sanitization or validation of the external web content is described in the skill.
Audit Metadata