plan-assets
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration defines a dependency on a remote MCP server at
https://mcp.trylexsis.com/mcp. This server provides the core logic and tools for the skill's operations. - [INDIRECT_PROMPT_INJECTION]: The
lexsis_asset_import.discovercapability allows the agent to scan external websites to find and import production assets, which introduces a risk of the agent encountering and acting upon malicious instructions embedded in those websites. - Ingestion points: Content from external websites processed by
lexsis_asset_import.discoverand files retrieved vialexsis_asset_import.import. - Boundary markers: No explicit delimiters or instructions are provided to the agent to prevent it from following commands found within the scanned web content.
- Capability inventory: The skill can perform batch imports, generate new assets, and modify the asset library within the linked storefront workspace.
- Sanitization: The instructions do not specify any sanitization or validation steps for the content retrieved from external sources.
Audit Metadata