site-mapping

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external content from websites, such as XML sitemaps and HTML navigation menus, which may contain malicious instructions (Indirect Prompt Injection).
  • Ingestion points: Untrusted data enters the agent context via browser_console fetch operations on sitemap XML files and DOM queries on site HTML.
  • Boundary markers: The skill does not implement delimiters or safety instructions to prevent the agent from executing instructions embedded in the retrieved web content.
  • Capability inventory: The skill utilizes the browser_console tool, which has capabilities for network access and browser-side script execution.
  • Sanitization: Extracted data is used directly as text content (textContent) without escaping or validation against a strict schema.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:55 AM
Security Audit — agent-trust-hub — site-mapping