zoho-inventory-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill instructions require the user to configure a third-party MCP server endpoint (https://rube.app/mcp). This creates a dependency on an external service not included in the trusted organizational whitelist provided in the security skill instructions.
- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8). Ingestion points: The agent retrieves tool definitions, slugs, and recommended execution plans dynamically via RUBE_SEARCH_TOOLS. Boundary markers: Absent; the instructions do not specify any delimiters or safety warnings to ignore potentially malicious instructions embedded within the fetched tool schemas. Capability inventory: The skill utilizes powerful tools such as RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH, which allow for significant action and remote tool execution based on the ingested data. Sanitization: Absent; there is no mention of validation or sanitization of the external tool metadata before the agent interprets and executes the tasks.
Audit Metadata