agentzia-optimize

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads competitor research reports and participant outputs from Agentzia's hosted MCP service, which processes public web pages and external AI assistant evaluations.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill connects to a remote Model Context Protocol server at an external URL to retrieve tool schemas and instructions that govern agent behavior, representing a third-party operational dependency with unknown or unverified publisher provenance.