finage-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill requires connection to an external MCP server hosted at https://rube.app/mcp. This domain is not included in the trusted organization list. Use of unverified external endpoints for tool definitions and execution logic introduces a reliance on the third-party provider's availability and integrity.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill is designed to ingest and act upon data retrieved dynamically from an external source via RUBE_SEARCH_TOOLS.
  • Ingestion points: Tool schemas and execution plans are fetched at runtime from rube.app.
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat the fetched schema data as untrusted or to ignore embedded instructions.
  • Capability inventory: The RUBE_MULTI_EXECUTE_TOOL capability allows the agent to perform external operations based on the fetched schemas.
  • Sanitization: There is no explicit sanitization logic; the agent is instructed to trust and use the exact field names and types returned by the remote search.
  • DYNAMIC_EXECUTION (LOW): The skill uses a pattern of dynamic tool discovery where the agent fetches and executes capabilities defined at runtime. While this is the intended functionality of the Rube/Composio integration, it shifts the security boundary to the external schema provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:42 PM