sitecore
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Installs the Membrane CLI package (
@membranehq/cli) from the official npm registry. This tool is provided by the vendor to facilitate secure communication between the agent and external APIs. - [COMMAND_EXECUTION]: Utilizes the
membranecommand-line utility to handle authentication flows, connection lifecycle management, and execution of Sitecore actions or raw API requests. - [INDIRECT_PROMPT_INJECTION]: The skill processes Sitecore data, creating a potential surface for indirect prompt injection.
- Ingestion points: Sitecore field values and API responses fetched via
membrane action runandmembrane requestcommands. - Boundary markers: No specific delimiters or instructions to treat external data as untrusted are included in the skill documentation.
- Capability inventory: The skill enables the agent to perform network-based API actions and read/write Sitecore data through the Membrane platform.
- Sanitization: Relies on standard platform-level safety measures for handling API data.
Audit Metadata