givebutter-automation

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill requires the user to connect to an external MCP server at https://rube.app/mcp. As this source is not part of the trusted organization list, it represents an unverifiable external dependency.
  • [PROMPT_INJECTION] (LOW): The skill utilizes a dynamic tool discovery and execution workflow (Category 8 surface). It ingests schemas and instructions from an external source to determine its execution plan. \n- Evidence Chain: \n
  • Ingestion points: Tool metadata and schemas are fetched at runtime via RUBE_SEARCH_TOOLS. \n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the search patterns. \n
  • Capability inventory: The skill can execute various Givebutter API operations, including data modification and retrieval, via RUBE_MULTI_EXECUTE_TOOL. \n
  • Sanitization: There is no evidence of input validation or sanitization for the data received from the external MCP server.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 01:44 AM