asin-data-api-automation
Warn
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Unverifiable Dependencies] (MEDIUM): The skill directs users to add https://rube.app/mcp as an MCP server. This domain is not a trusted source, presenting a risk of untrusted remote infrastructure.
- [Indirect Prompt Injection] (MEDIUM): The skill processes data from the Asin Data API and dynamically discovers tools via RUBE_SEARCH_TOOLS. There are no boundary markers or sanitization logic to prevent malicious content in API responses from influencing agent behavior. Evidence: 1. Ingestion: API responses and tool discovery; 2. Boundary: Absent; 3. Capability: RUBE_MULTI_EXECUTE_TOOL, RUBE_REMOTE_WORKBENCH; 4. Sanitization: Absent.
- [Dynamic Execution] (MEDIUM): RUBE_REMOTE_WORKBENCH allows for remote execution of tools, which could lead to unauthorized actions if the remote environment is compromised or receives malicious instructions.
Audit Metadata