oray

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

• Third-party content exposure detected (low risk: 0.10). The agent reads web pages and catalog data from oray.com via API tools, which involves fetching external content from the target website upon user request (low risk).

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill configures a remote Model Context Protocol (MCP) server and REST API endpoints hosted at unbrowse.ai, which provides executable instructions and tool definitions that govern the agent's runtime behavior. Because unbrowse.ai is a third-party/community-operated platform without strong first-party provenance, this constitutes a common/reputable unofficial operational dependency.