crawl-site
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection through its core functionality. Ingestion points: Data is ingested from external URLs via tools like start_crawl and results are reviewed using get_site_tree and status reports. Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the crawled content. Capability inventory: The skill uses Crawlio-specific tools (update_settings, start_crawl, get_crawl_status, get_failed_urls, get_errors, get_site_tree, recrawl_urls) and does not include general-purpose shell execution or file system write capabilities. Sanitization: No sanitization or filtering of crawled content is mentioned before it is processed by the agent.
Audit Metadata