coupa-automation

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill connects to an external MCP server at rube.app (Composio's infrastructure) to fetch tool schemas and execute capabilities.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Coupa API responses, which constitutes an indirect prompt injection attack surface.
  • Ingestion points: Data retrieved from Coupa operations (e.g., invoice details, supplier info, search results) enters the agent context via RUBE_SEARCH_TOOLS and tool execution outputs.
  • Boundary markers: The provided instructions do not specify any delimiters or ignore-instructions for the external data.
  • Capability inventory: The skill has the ability to execute various Coupa tools via RUBE_MULTI_EXECUTE_TOOL and perform batch operations using RUBE_REMOTE_WORKBENCH.
  • Sanitization: There is no mention of explicit sanitization or validation of the content retrieved from Coupa.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 09:18 PM