amazon-sorftime-research-mcp-skill

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required workflow queries MCP APIs and reads Amazon product reviews, listings, and customer feedback which can contain untrusted external text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The configuration guide provides example URLs for external MCP services (https://mcp.sorftime.com, https://mcp.sif.com, https://mcp.xiyou.com) which the skill instructs the agent to configure and query at runtime, but these are third-party unofficial services lacking strong first-party provenance, making them a medium-tier operational dependency.