amazon-ads-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a functional guide for an Amazon Advertising MCP server. It uses standard API identifiers (integration_id, account_id) and follows best practices for tool interaction.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Amazon Advertising reports and product metadata via tools like
ask_report_analyst. While this represents an ingestion point for untrusted data, the agent's actions are restricted to campaign management and data analysis within the provided toolset, with no access to high-privilege operations like shell execution or file system writes. - [DATA_EXPOSURE_EXFILTRATION]: No evidence of hardcoded credentials or unauthorized data transmission was found. The skill uses appropriate scoping for advertising data access.
Audit Metadata