coinmarketcal-automation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [External Downloads] (LOW): The skill requires the user to add an external MCP endpoint
https://rube.app/mcp. This domain is not listed as a trusted external source, though it is necessary for the skill's primary function. - [Remote Code Execution] (LOW): The skill uses
RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCHto execute tasks on remote infrastructure. While this is the intended purpose, it grants the agent the ability to perform actions in a remote environment based on external input. - [Prompt Injection] (LOW): The skill is vulnerable to indirect prompt injection (Category 8). \n
- Ingestion points: Tool schemas and execution plans are fetched dynamically from the
RUBE_SEARCH_TOOLSendpoint and external API responses. \n - Boundary markers: None provided; the instructions tell the agent to follow the returned schemas and arguments exactly. \n
- Capability inventory: Remote execution capabilities via
RUBE_MULTI_EXECUTE_TOOLandRUBE_REMOTE_WORKBENCH. \n - Sanitization: No sanitization or validation of the remote tool schemas is performed before execution.
Audit Metadata