analyze-page
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Configures a connection to an external Model Context Protocol (MCP) server at https://mcp.trylexsis.com/mcp to provide storefront analysis capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external URLs and screenshots, creating a surface for indirect prompt injection attacks.
- Ingestion points: Page URLs, desktop and mobile views, and creative screenshots (SKILL.md).
- Boundary markers: Absent; there are no instructions provided to the agent to treat content within the analyzed pages as untrusted or to ignore instructions embedded in those pages.
- Capability inventory: Host browser interaction (inspecting headings, media, and interactions) and access to Lexsis analysis tools via the MCP server.
- Sanitization: Absent; the Brand Safety section focuses on filtering output content for brand consistency rather than sanitizing input data to prevent instruction injection.
Audit Metadata