textrazor-automation

Warn

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill directs the user to add an external MCP server endpoint https://rube.app/mcp. This domain is not on the Trusted External Sources list, representing a dependency on an unverified third-party service.
  • [DYNAMIC_EXECUTION] (MEDIUM): The workflow uses RUBE_SEARCH_TOOLS to dynamically fetch tool schemas and execution plans, which are then executed via RUBE_MULTI_EXECUTE_TOOL. This pattern executes code/logic defined at runtime by a remote server.
  • [INDIRECT_PROMPT_INJECTION] (LOW):
  • Ingestion points: Tool schemas, input definitions, and recommended execution plans returned by RUBE_SEARCH_TOOLS.
  • Boundary markers: Absent; the skill instructs the agent to use the returned fields exactly as provided.
  • Capability inventory: RUBE_MULTI_EXECUTE_TOOL (tool execution), RUBE_REMOTE_WORKBENCH (bulk operations).
  • Sanitization: Absent; no validation or escaping is mentioned for the data returned by the search tool.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 18, 2026, 01:43 AM