esignatures-io-automation
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to the Rube MCP service at
https://rube.app/mcpto fetch tool configurations and schemas. This is a functional requirement for the toolkit discovery process. - [COMMAND_EXECUTION]: The skill utilizes
RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCHto perform automation tasks based on discovered tool slugs and arguments. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests tool definitions and execution plans from an external provider.
- Ingestion points: Tool schemas and use-case recommendations retrieved via
RUBE_SEARCH_TOOLSfromSKILL.md. - Boundary markers: Absent; instructions direct the agent to follow returned execution plans without verification.
- Capability inventory: Includes tool execution via
RUBE_MULTI_EXECUTE_TOOLand connection management viaRUBE_MANAGE_CONNECTIONS. - Sanitization: No explicit validation or sanitization steps are described for the dynamic schemas returned from the remote service.
Audit Metadata