firecrawl-crawl
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of content from external websites via the
firecrawl crawlcommand. This creates a surface where instructions embedded in the crawled pages could potentially influence agent behavior. \n - Ingestion points: The
firecrawl crawlcommand inSKILL.mdtakes a user-provided URL and retrieves site content. \n - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts in the crawled content. \n
- Capability inventory: The skill permits execution of the
firecrawlandnpx firecrawl-clicommands. \n - Sanitization: The instructions do not describe sanitization or validation of the retrieved web content. \n
- [EXTERNAL_DOWNLOADS]: The skill mentions using
npx firecrawl-cli, which downloads the official Firecrawl command-line utility from the NPM registry. This is standard behavior for vendor-provided developer tooling.
Audit Metadata