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_consolefetch 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_consoletool, 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